# Pulltrader

> Trading-card research and seller economics: identify cards, check sold comps, and compare fees.

- name: app.pulltrader/seller-economics
- version: 0.6.1
- connection class: R2 (oauth_consent_once)
- trust: 100/100
- quality: 72/100 (needs work)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/app.pulltrader%2Fseller-economics
- tools: https://api.protogrid.dev/v1/servers/app.pulltrader%2Fseller-economics/tools

**An agent can connect after a one-time OAuth consent by a human.** Remote endpoint behind OAuth 2. Tokens stay with the agent; the registry only exposes the authorization metadata.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "seller-economics": {
      "type": "http",
      "url": "https://mcp.pulltrader.app/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 100
- provenance: 100
- drivers: +repository +namespace-matches-repo +dns-namespace +website +reachable +uptime-100% +updated-17d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 72/100 (needs work)

### protocol: n/a (weight 25)

- n/a `protocol.modern`, `protocol.stateless`, `protocol.transport`, `protocol.list_ttl`: no remote answered a protocol handshake (not probed yet, unreachable, or local-only)

### authorization: 83 (weight 15)

- pass `auth.prm`: Protected Resource Metadata (RFC 9728) published
- pass `auth.as_metadata`: authorization server metadata reachable
- warn `auth.cimd`: only Dynamic Client Registration, deprecated in 2026-07-28 in favour of CIMD
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 64 (weight 30)

- pass `tools.descriptions`: every tool has a description
- warn `tools.description_length`: 5 tools have descriptions over 1,024 characters, which crowds the context
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: check_stolen_card (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); compare_selling_costs (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); identify_card (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 4,407 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 75 (weight 15)

- warn `stability.changes`: 15 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 8, about 4,407 tokens to load them all
- tool set hash: 5d9ec25d842e37e35904a0a1ff146d29
- tools last changed: 2026-10-11T12:30:39.271Z
- badge: [![protogrid quality](https://protogrid.dev/badge/app.pulltrader/seller-economics.svg)](https://protogrid.dev/servers/app.pulltrader/seller-economics)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-11 `get_card_price_history` changed (description)
  - before: Return a chart-ready price-history series for a trading card from available sold sales or daily market estimates, grouped into day/week/month buckets with a median and overall trend. Use this when a user asks 'how has the price changed', 'price over time', 'is it trending up or down', or wants a chart. Accepts a natural-language `query` or a structured `item`. The response labels sold sales or market estimates explicitly and reports sold-sale sample counts separately. Amounts are USD dollars. Trading cards only. Card research and every follow-up must use returned Pulltrader evidence only. Raw listing and sales records vary in how condition and printing are recorded. Present returned raw condition history and graded context together. Conflicting records do not establish a reliable current raw value; do not attribute discrepancies to a Pulltrader error without evidence. Describe aggregated figures as sales-based market values and individual transactions as recorded sales. Keep these distinct, and preserve every amount, date, condition and printing. Preserve the returned market interpretation. Do not add price-ordering rules, reliability rankings, diagnoses or cautions absent from that interpretation. Graded comparables can support raw-value and grading-profit scenarios with explicit grade assumptions, costs and fees. Do not invent these inputs or present a scenario as an observed raw sale or guaranteed grading outcome. Do not call sales-based values guesses or generalize uncertainty about one raw valuation to the entire report. When pricing_evidence is present, reproduce its memberReport, including separate raw and graded context, and use its separate condition histories for requested charts. Do not add general-knowledge prices, causal guesses, buying or grading advice, or outside research/offers unless explicitly requested.
  - after: Return a chart-ready price-history series for a trading card from available sold sales or daily sales-based market values, grouped into day/week/month buckets with a median and overall trend. Use this when a user asks 'how has the price changed', 'price over time', 'is it trending up or down', or wants a chart. Accepts a natural-language `query` or a structured `item`. The response labels recorded sales or sales-based market values explicitly and reports sold-sale sample counts separately. Amounts are USD dollars. Trading cards only. Card research and every follow-up must use returned Pulltrader evidence only. Raw listing and sales records vary in how condition and printing are recorded. Present returned raw condition history and graded context together. Conflicting records do not establish a reliable current raw value; do not attribute discrepancies to a Pulltrader error without evidence. Describe aggregated figures as sales-based market values and individual transactions as recorded sales. Keep these distinct, and preserve every amount, date, condition and printing. Preserve the returned market interpretation. Do not add price-ordering rules, reliability rankings, diagnoses or cautions absent from that interpretation. Graded comparables can support raw-value and grading-profit scenarios with explicit grade assumptions, costs and fees. Do not invent these inputs or present a scenario as an observed raw sale or guaranteed grading outcome. Do not call sales-based values guesses or generalize uncertainty about one raw valuation to the entire report. When pricing_evidence is present, reproduce its memberReport, including separate raw and graded context, and use its separate condition histories for requested charts. Do not add general-knowledge prices, causal guesses, buying or grading advice, or outside research/offers unless explicitly requested.
- 2026-10-11 `search_card_sales` changed (description)
  - before: Return a capped sample of recent comparable SOLD listings for a trading card (price + sale date), plus a market snapshot (median, range, sample size). Use this when a user asks 'what is this card selling for', 'recent sales', or 'comps'. Accepts a natural-language `query` or a structured `item`. Figures are estimates from recent sales and exclude fees/taxes/shipping; this is not financial advice and does not place orders. Trading cards only. Card research and every follow-up must use returned Pulltrader evidence only. Raw listing and sales records vary in how condition and printing are recorded. Present returned raw condition history and graded context together. Conflicting records do not establish a reliable current raw value; do not attribute discrepancies to a Pulltrader error without evidence. Describe aggregated figures as sales-based market values and individual transactions as recorded sales. Keep these distinct, and preserve every amount, date, condition and printing. Preserve the returned market interpretation. Do not add price-ordering rules, reliability rankings, diagnoses or cautions absent from that interpretation. Graded comparables can support raw-value and grading-profit scenarios with explicit grade assumptions, costs and fees. Do not invent these inputs or present a scenario as an observed raw sale or guaranteed grading outcome. Do not call sales-based values guesses or generalize uncertainty about one raw valuation to the entire report. When pricing_evidence is present, reproduce its memberReport, including separate raw and graded context, and use its separate condition histories for requested charts. Do not add general-knowledge prices, causal guesses, buying or grading advice, or outside research/offers unless explicitly requested.
  - after: Return a capped sample of recent comparable SOLD listings for a trading card (price + sale date), plus a market snapshot (median, range, sample size). Use this when a user asks 'what is this card selling for', 'recent sales', or 'comps'. Accepts a natural-language `query` or a structured `item`. Values are based on recorded sales and exclude fees/taxes/shipping; this is not financial advice and does not place orders. Trading cards only. Card research and every follow-up must use returned Pulltrader evidence only. Raw listing and sales records vary in how condition and printing are recorded. Present returned raw condition history and graded context together. Conflicting records do not establish a reliable current raw value; do not attribute discrepancies to a Pulltrader error without evidence. Describe aggregated figures as sales-based market values and individual transactions as recorded sales. Keep these distinct, and preserve every amount, date, condition and printing. Preserve the returned market interpretation. Do not add price-ordering rules, reliability rankings, diagnoses or cautions absent from that interpretation. Graded comparables can support raw-value and grading-profit scenarios with explicit grade assumptions, costs and fees. Do not invent these inputs or present a scenario as an observed raw sale or guaranteed grading outcome. Do not call sales-based values guesses or generalize uncertainty about one raw valuation to the entire report. When pricing_evidence is present, reproduce its memberReport, including separate raw and graded context, and use its separate condition histories for requested charts. Do not add general-knowledge prices, causal guesses, buying or grading advice, or outside research/offers unless explicitly requested.
- 2026-10-11 `calculate_required_sale_price` changed (description, inputSchema)
  - before: Given a target take-home amount, compute the per-item sale price a trading-card seller must list at to net that amount on ONE selling method, after fees — eBay (estimated), a Pulltrader selling method (marketplace, Fulfilled by Pulltrader, branded storefront, in-person POS), or an estimated competitor marketplace (TCGplayer, Mana Pool, Misprint, Fanatics Collect, Goldin). If acquisition_cost is supplied, the target is treated as net profit (payout minus what you paid); otherwise it is the take-home payout. Use this when a seller asks 'what do I need to list this at to walk away with $X', 'to net/profit $X after fees', or 'to break even'. Calculations are deterministic and use dated fee schedules. Do NOT use this to look up a card's market value or recent sales (this tool does not price cards), and do NOT use it for non-trading-card categories. Present eBay and competitor figures as estimates, never as guaranteed proceeds.
  - after: Given a target take-home amount, compute the per-item sale price a trading-card seller must list at to net that amount on ONE selling method, after fees — eBay (estimated), a Pulltrader selling method (marketplace, Fulfilled by Pulltrader, branded storefront, in-person POS), or an estimated competitor marketplace (TCGplayer, Mana Pool, Misprint, Fanatics Collect, Goldin). If acquisition_cost is supplied, the target is treated as net profit (payout minus what you paid); otherwise it is the take-home payout. Use shipping_cost for actual seller postage, separate from shipping_amount charged to the buyer. Never adjust target_net to account for postage yourself. Use this when a seller asks 'what do I need to list this at to walk away with $X', 'to net/profit $X after fees', or 'to break even'. Calculations are deterministic and use dated fee schedules. Do NOT use this to look up a card's market value or recent sales (this tool does not price cards), and do NOT use it for non-trading-card categories. Present eBay and competitor figures as estimates, never as guaranteed proceeds.
- 2026-10-11 `get_card_price_history` changed (description)
  - before: Return a chart-ready price-history series for a trading card from available sold sales or daily market estimates, grouped into day/week/month buckets with a median and overall trend. Use this when a user asks 'how has the price changed', 'price over time', 'is it trending up or down', or wants a chart. Accepts a natural-language `query` or a structured `item`. The response labels sold sales or market estimates explicitly and reports sold-sale sample counts separately. Amounts are USD dollars. Trading cards only. Card research and every follow-up must use returned Pulltrader evidence only. If estimates conflict, the cause and current value are unknown. When pricing_evidence is present, reproduce its memberReport and use its separate condition histories for requested charts. Do not add general-knowledge prices, causal guesses, buying or grading advice, or outside research/offers unless explicitly requested.
  - after: Return a chart-ready price-history series for a trading card from available sold sales or daily market estimates, grouped into day/week/month buckets with a median and overall trend. Use this when a user asks 'how has the price changed', 'price over time', 'is it trending up or down', or wants a chart. Accepts a natural-language `query` or a structured `item`. The response labels sold sales or market estimates explicitly and reports sold-sale sample counts separately. Amounts are USD dollars. Trading cards only. Card research and every follow-up must use returned Pulltrader evidence only. Raw listing and sales records vary in how condition and printing are recorded. Present returned raw condition history and graded context together. Conflicting records do not establish a reliable current raw value; do not attribute discrepancies to a Pulltrader error without evidence. Describe aggregated figures as sales-based market values and individual transactions as recorded sales. Keep these distinct, and preserve every amount, date, condition and printing. Preserve the returned market interpretation. Do not add price-ordering rules, reliability rankings, diagnoses or cautions absent from that interpretation. Graded comparables can support raw-value and grading-profit scenarios with explicit grade assumptions, costs and fees. Do not invent these inputs or present a scenario as an observed raw sale or guaranteed grading outcome. Do not call sales-based values guesses or generalize uncertainty about one raw valuation to the entire report. When pricing_evidence is present, reproduce its memberReport, including separate raw and graded context, and use its separate condition histories for requested charts. Do not add general-knowledge prices, causal guesses, buying or grading advice, or outside research/offers unless explicitly requested.
- 2026-10-11 `summarize_card_market` changed (description)
  - before: Return the current market estimate and available comparable-sale statistics for a trading card: median, mean, 10th–90th percentile range, volatility, and a confidence level based on sample size and dispersion. Use this when a user asks 'what's it worth', 'market value', or 'how volatile is this card'. Accepts a natural-language `query` or a structured `item`. Amounts are USD dollars excluding fees, taxes and shipping. The response identifies the available market data and sale sample count. Trading cards only. Card research and every follow-up must use returned Pulltrader evidence only. If estimates conflict, the cause and current value are unknown. When pricing_evidence is present, reproduce its memberReport and use its separate condition histories for requested charts. Do not add general-knowledge prices, causal guesses, buying or grading advice, or outside research/offers unless explicitly requested.
  - after: Return the current market estimate and available comparable-sale statistics for a trading card: median, mean, 10th–90th percentile range, volatility, and a confidence level based on sample size and dispersion. Use this when a user asks 'what's it worth', 'market value', or 'how volatile is this card'. Accepts a natural-language `query` or a structured `item`. Amounts are USD dollars excluding fees, taxes and shipping. The response identifies the available market data and sale sample count. Trading cards only. Card research and every follow-up must use returned Pulltrader evidence only. Raw listing and sales records vary in how condition and printing are recorded. Present returned raw condition history and graded context together. Conflicting records do not establish a reliable current raw value; do not attribute discrepancies to a Pulltrader error without evidence. Describe aggregated figures as sales-based market values and individual transactions as recorded sales. Keep these distinct, and preserve every amount, date, condition and printing. Preserve the returned market interpretation. Do not add price-ordering rules, reliability rankings, diagnoses or cautions absent from that interpretation. Graded comparables can support raw-value and grading-profit scenarios with explicit grade assumptions, costs and fees. Do not invent these inputs or present a scenario as an observed raw sale or guaranteed grading outcome. Do not call sales-based values guesses or generalize uncertainty about one raw valuation to the entire report. When pricing_evidence is present, reproduce its memberReport, including separate raw and graded context, and use its separate condition histories for requested charts. Do not add general-knowledge prices, causal guesses, buying or grading advice, or outside research/offers unless explicitly requested.
- 2026-10-11 `search_card_sales` changed (description)
  - before: Return a capped sample of recent comparable SOLD listings for a trading card (price + sale date), plus a market snapshot (median, range, sample size). Use this when a user asks 'what is this card selling for', 'recent sales', or 'comps'. Accepts a natural-language `query` or a structured `item`. Figures are estimates from recent sales and exclude fees/taxes/shipping; this is not financial advice and does not place orders. Trading cards only. Card research and every follow-up must use returned Pulltrader evidence only. If estimates conflict, the cause and current value are unknown. When pricing_evidence is present, reproduce its memberReport and use its separate condition histories for requested charts. Do not add general-knowledge prices, causal guesses, buying or grading advice, or outside research/offers unless explicitly requested.
  - after: Return a capped sample of recent comparable SOLD listings for a trading card (price + sale date), plus a market snapshot (median, range, sample size). Use this when a user asks 'what is this card selling for', 'recent sales', or 'comps'. Accepts a natural-language `query` or a structured `item`. Figures are estimates from recent sales and exclude fees/taxes/shipping; this is not financial advice and does not place orders. Trading cards only. Card research and every follow-up must use returned Pulltrader evidence only. Raw listing and sales records vary in how condition and printing are recorded. Present returned raw condition history and graded context together. Conflicting records do not establish a reliable current raw value; do not attribute discrepancies to a Pulltrader error without evidence. Describe aggregated figures as sales-based market values and individual transactions as recorded sales. Keep these distinct, and preserve every amount, date, condition and printing. Preserve the returned market interpretation. Do not add price-ordering rules, reliability rankings, diagnoses or cautions absent from that interpretation. Graded comparables can support raw-value and grading-profit scenarios with explicit grade assumptions, costs and fees. Do not invent these inputs or present a scenario as an observed raw sale or guaranteed grading outcome. Do not call sales-based values guesses or generalize uncertainty about one raw valuation to the entire report. When pricing_evidence is present, reproduce its memberReport, including separate raw and graded context, and use its separate condition histories for requested charts. Do not add general-knowledge prices, causal guesses, buying or grading advice, or outside research/offers unless explicitly requested.
- 2026-10-11 `check_kapture_cert` removed
  - Check an exact certification number against Kapture. Preserve leading zeros. CLEAN means no verified stolen report matched, not proof of authenticity or ownership. STOLEN includes a voluntary recovery form link. Never infer possession from a lookup or send personal details through this tool.
- 2026-10-11 `get_card_price_history` changed (description)
  - before: Return a chart-ready price-history series for a trading card from available sold sales or daily market estimates, grouped into day/week/month buckets with a median and overall trend. Use this when a user asks 'how has the price changed', 'price over time', 'is it trending up or down', or wants a chart. Accepts a natural-language `query` or a structured `item`. The response labels sold sales or market estimates explicitly and reports sold-sale sample counts separately. Amounts are USD dollars. Trading cards only.
  - after: Return a chart-ready price-history series for a trading card from available sold sales or daily market estimates, grouped into day/week/month buckets with a median and overall trend. Use this when a user asks 'how has the price changed', 'price over time', 'is it trending up or down', or wants a chart. Accepts a natural-language `query` or a structured `item`. The response labels sold sales or market estimates explicitly and reports sold-sale sample counts separately. Amounts are USD dollars. Trading cards only. Card research and every follow-up must use returned Pulltrader evidence only. If estimates conflict, the cause and current value are unknown. When pricing_evidence is present, reproduce its memberReport and use its separate condition histories for requested charts. Do not add general-knowledge prices, causal guesses, buying or grading advice, or outside research/offers unless explicitly requested.
- 2026-10-11 `summarize_card_market` changed (description)
  - before: Return the current market estimate and available comparable-sale statistics for a trading card: median, mean, 10th–90th percentile range, volatility, and a confidence level based on sample size and dispersion. Use this when a user asks 'what's it worth', 'market value', or 'how volatile is this card'. Accepts a natural-language `query` or a structured `item`. Amounts are USD dollars excluding fees, taxes and shipping. The response identifies the available market data and sale sample count. Trading cards only.
  - after: Return the current market estimate and available comparable-sale statistics for a trading card: median, mean, 10th–90th percentile range, volatility, and a confidence level based on sample size and dispersion. Use this when a user asks 'what's it worth', 'market value', or 'how volatile is this card'. Accepts a natural-language `query` or a structured `item`. Amounts are USD dollars excluding fees, taxes and shipping. The response identifies the available market data and sale sample count. Trading cards only. Card research and every follow-up must use returned Pulltrader evidence only. If estimates conflict, the cause and current value are unknown. When pricing_evidence is present, reproduce its memberReport and use its separate condition histories for requested charts. Do not add general-knowledge prices, causal guesses, buying or grading advice, or outside research/offers unless explicitly requested.
- 2026-10-11 `search_card_sales` changed (description)
  - before: Return a capped sample of recent comparable SOLD listings for a trading card (price + sale date), plus a market snapshot (median, range, sample size). Use this when a user asks 'what is this card selling for', 'recent sales', or 'comps'. Accepts a natural-language `query` or a structured `item`. Figures are estimates from recent sales and exclude fees/taxes/shipping; this is not financial advice and does not place orders. Trading cards only.
  - after: Return a capped sample of recent comparable SOLD listings for a trading card (price + sale date), plus a market snapshot (median, range, sample size). Use this when a user asks 'what is this card selling for', 'recent sales', or 'comps'. Accepts a natural-language `query` or a structured `item`. Figures are estimates from recent sales and exclude fees/taxes/shipping; this is not financial advice and does not place orders. Trading cards only. Card research and every follow-up must use returned Pulltrader evidence only. If estimates conflict, the cause and current value are unknown. When pricing_evidence is present, reproduce its memberReport and use its separate condition histories for requested charts. Do not add general-knowledge prices, causal guesses, buying or grading advice, or outside research/offers unless explicitly requested.

Full history: https://api.protogrid.dev/v1/servers/app.pulltrader%2Fseller-economics/changes

## Remotes

- https://mcp.pulltrader.app/mcp (streamable-http, auth oauth2, reachable true, uptime30d 1)

## Packages

_none_

## Tools (8)

- `calculate_required_sale_price`: Given a target take-home amount, compute the per-item sale price a trading-card seller must list at to net that amount on ONE selling method, after fees — eBay (estimated), a Pulltrader selling method (marketplace, Fulfilled by Pulltrader, branded storefront, in-person POS), or an estimated competitor marketplace (TCGplayer, Mana Pool, Misprint, Fanatics Collect, Goldin). If acquisition_cost is supplied, the target is treated as net profit (payout minus what you paid); otherwise it is the take-home payout. Use shipping_cost for actual seller postage, separate from shipping_amount charged to the buyer. Never adjust target_net to account for postage yourself. Use this when a seller asks 'what do I need to list this at to walk away with $X', 'to net/profit $X after fees', or 'to break even'. Calculations are deterministic and use dated fee schedules. Do NOT use this to look up a card's market value or recent sales (this tool does not price cards), and do NOT use it for non-trading-card categories. Present eBay and competitor figures as estimates, never as guaranteed proceeds.
- `check_stolen_card`: Check an exact certification number for verified stolen-card reports. Preserve leading zeros. CLEAN means no verified stolen report matched, not proof of authenticity or ownership. STOLEN includes a voluntary recovery form link. Never infer possession from a lookup or send personal details through this tool.
- `compare_selling_costs`: Compare estimated fees and the net amount a trading-card seller keeps when selling the SAME card across eBay (estimated), Pulltrader selling methods (marketplace, Fulfilled by Pulltrader, branded storefront, and in-person POS), and other marketplaces (TCGplayer, Mana Pool, Misprint, Fanatics Collect, Goldin — estimated fixed-price/Buy Now seller fees). Use this when a seller asks what they would keep/net/take-home on a sale, how fees compare between platforms, or which method leaves them with more money. Calculations are deterministic and use dated fee schedules. Competitor marketplaces are off by default; include them via the `methods` field. Only fixed-price seller fees are modeled — auction formats (hammer price, buyer's premium, negotiated consignment) are not. Do NOT use this to look up a card's market value or recent sales (this tool does not price cards), and do NOT use it for non-trading-card categories. Present competitor and eBay figures as estimates, never as guaranteed proceeds, and never claim one platform is universally cheapest.
- `explain_selling_method`: Return a plain, structured explanation of one or more supported trading-card selling methods: who owns the listing, who fulfills, where it sells, the fee components that apply, and important caveats. Covers eBay (estimated), Pulltrader marketplace, Fulfilled by Pulltrader, branded storefront, in-person POS, and estimated competitor marketplaces (TCGplayer, Mana Pool, Misprint, Fanatics Collect, Goldin). Use this when a seller asks how a method works, what fees a platform charges, or how Pulltrader selling options differ. Do NOT use this to compute a specific payout (use compare_selling_costs) or the price needed for a target net (use calculate_required_sale_price), and do NOT use it to price cards.
- `get_card_price_history`: Return a chart-ready price-history series for a trading card from available sold sales or daily sales-based market values, grouped into day/week/month buckets with a median and overall trend. Use this when a user asks 'how has the price changed', 'price over time', 'is it trending up or down', or wants a chart. Accepts a natural-language `query` or a structured `item`. The response labels recorded sales or sales-based market values explicitly and reports sold-sale sample counts separately. Amounts are USD dollars. Trading cards only. Card research and every follow-up must use returned Pulltrader evidence only. Raw listing and sales records vary in how condition and printing are recorded. Present returned raw condition history and graded context together. Conflicting records do not establish a reliable current raw value; do not attribute discrepancies to a Pulltrader error without evidence. Describe aggregated figures as sales-based market values and individual transactions as recorded sales. Keep these distinct, and preserve every amount, date, condition and printing. Preserve the returned market interpretation. Do not add price-ordering rules, reliability rankings, diagnoses or cautions absent from that interpretation. Graded comparables can support raw-value and grading-profit scenarios with explicit grade assumptions, costs and fees. Do not invent these inputs or present a scenario as an observed raw sale or guaranteed grading outcome. Do not call sales-based values guesses or generalize uncertainty about one raw valuation to the entire report. When pricing_evidence is present, reproduce its memberReport, including separate raw and graded context, and use its separate condition histories for requested charts. Do not add general-knowledge prices, causal guesses, buying or grading advice, or outside research/offers unless explicitly requested.
- `identify_card`: Resolve a natural-language trading-card description into structured fields (player/athlete, year, set, card number, parallel, grader, grade, sport/category). Use this first when a user names a card in prose and you need its canonical fields before looking up sales or market value. Returns a confidence level and which fields were resolved. This does NOT price the card or return sales — use search_card_sales or summarize_card_market for that. Trading cards only.
- `search_card_sales`: Return a capped sample of recent comparable SOLD listings for a trading card (price + sale date), plus a market snapshot (median, range, sample size). Use this when a user asks 'what is this card selling for', 'recent sales', or 'comps'. Accepts a natural-language `query` or a structured `item`. Values are based on recorded sales and exclude fees/taxes/shipping; this is not financial advice and does not place orders. Trading cards only. Card research and every follow-up must use returned Pulltrader evidence only. Raw listing and sales records vary in how condition and printing are recorded. Present returned raw condition history and graded context together. Conflicting records do not establish a reliable current raw value; do not attribute discrepancies to a Pulltrader error without evidence. Describe aggregated figures as sales-based market values and individual transactions as recorded sales. Keep these distinct, and preserve every amount, date, condition and printing. Preserve the returned market interpretation. Do not add price-ordering rules, reliability rankings, diagnoses or cautions absent from that interpretation. Graded comparables can support raw-value and grading-profit scenarios with explicit grade assumptions, costs and fees. Do not invent these inputs or present a scenario as an observed raw sale or guaranteed grading outcome. Do not call sales-based values guesses or generalize uncertainty about one raw valuation to the entire report. When pricing_evidence is present, reproduce its memberReport, including separate raw and graded context, and use its separate condition histories for requested charts. Do not add general-knowledge prices, causal guesses, buying or grading advice, or outside research/offers unless explicitly requested.
- `summarize_card_market`: Return the current market estimate and available comparable-sale statistics for a trading card: median, mean, 10th–90th percentile range, volatility, and a confidence level based on sample size and dispersion. Use this when a user asks 'what's it worth', 'market value', or 'how volatile is this card'. Accepts a natural-language `query` or a structured `item`. Amounts are USD dollars excluding fees, taxes and shipping. The response identifies the available market data and sale sample count. Trading cards only. Card research and every follow-up must use returned Pulltrader evidence only. Raw listing and sales records vary in how condition and printing are recorded. Present returned raw condition history and graded context together. Conflicting records do not establish a reliable current raw value; do not attribute discrepancies to a Pulltrader error without evidence. Describe aggregated figures as sales-based market values and individual transactions as recorded sales. Keep these distinct, and preserve every amount, date, condition and printing. Preserve the returned market interpretation. Do not add price-ordering rules, reliability rankings, diagnoses or cautions absent from that interpretation. Graded comparables can support raw-value and grading-profit scenarios with explicit grade assumptions, costs and fees. Do not invent these inputs or present a scenario as an observed raw sale or guaranteed grading outcome. Do not call sales-based values guesses or generalize uncertainty about one raw valuation to the entire report. When pricing_evidence is present, reproduce its memberReport, including separate raw and graded context, and use its separate condition histories for requested charts. Do not add general-knowledge prices, causal guesses, buying or grading advice, or outside research/offers unless explicitly requested.