OpenShopGraph

Quality 97 / 100strong

9 tools, about 3,427 tokens to load them all · tool set d966cf9f8c08 · tools last changed 2026-10-18 · checked 2026-10-20 11:08 UTC

Tool changes

• 2026-10-18get_shipping_policychangeddescription
  before

  What a shop STATES about its own shipping: which destinations it names, the delivery time it claims, and any free-shipping threshold — plus the date that statement was last checked and where it was read (policy_page or structured_data). This is a shop-level statement, NOT an offer and NOT a quote: it carries no carrier and no shipping price, because OpenShopGraph does not hold that data. Pass country (ISO 3166-1 alpha-2, e.g. "DE") to get a ships_to verdict derived from the stated destination list — "unknown" is a real answer there and means the statement does not settle it. When nothing has been collected for a shop, the reply says so explicitly (collected:false): that is a gap in the data, not a statement that the shop does not ship. Relaying the checked-at date alongside any figure keeps a stale merchant claim from being read as a current fact.

  after · 94% of words in common

  Alias of get_shop_policies (same answer, kept for existing integrations). What a shop STATES about its own shipping: which destinations it names, the delivery time it claims, and any free-shipping threshold — plus the date that statement was last checked and where it was read (policy_page or structured_data). This is a shop-level statement, NOT an offer and NOT a quote: it carries no carrier and no shipping price, because OpenShopGraph does not hold that data. Pass country (ISO 3166-1 alpha-2, e.g. "DE") to get a ships_to verdict derived from the stated destination list — "unknown" is a real answer there and means the statement does not settle it. When nothing has been collected for a shop, the reply says so explicitly (collected:false): that is a gap in the data, not a statement that the shop does not ship. Relaying the checked-at date alongside any figure keeps a stale merchant claim from being read as a current fact.

• 2026-10-18get_shop_policiesadded

  What a shop STATES about its own policies, each fact with the date it was last checked and where it was read: return window in days (returns_days), free return label, tracking offered, payment methods, buyer-protection seal, plus the shipping statement (destinations, stated delivery time, free-shipping threshold). Use it for questions such as "how long can I return something at this shop?". These are shop-level statements, NOT offers and NOT quotes: no carrier, no shipping price. Every fact in `policies` is an object with `collected`: when true it carries value, checked_at and source (policy_page = read from the shop, llm_gap_resolution = model-derived, say so when relaying); when false it carries a reason and means OpenShopGraph holds no checked value — a gap in the data, NOT a statement that the shop has no such policy. A fact whose value and check date are stored but whose source is unknown is also reported as collected:false (reason no_source): a value without a source is never shown. Pass country (ISO 3166-1 alpha-2, e.g. "DE") to get a ships_to verdict derived from the stated destination list — "unknown" is a real answer there. Relay checked_at alongside any figure so a stale claim is not read as current. `get_shipping_policy` is the earlier name of this tool and returns the same answer.

• 2026-10-17find_shopchangeddescription
  before

  Search merchants/shops by free-text query (name or domain fragment), optionally filtered by country (ISO 3166-1 alpha-2, e.g. "DE") and/or by an EXACT category slug. Returns the public shop view only — shops still under internal review are never returned. `results` carries at most `limit` entries (default 50, max 100); `total_count` is the full match count before that cap and `truncated` is true when more results exist beyond this page — raise `offset` (default 0) to page through them. Multi-word queries are matched conjunctively: every word must be evidenced on a shop (name, domain or category). `ignored_terms` lists the words that matched nothing anywhere in the corpus and were therefore dropped to avoid an empty answer — a non-empty `ignored_terms` means the results answer a NARROWER question than you asked, so do not present them as satisfying those words. `category_truncated` is true when category resolution hit its internal cap and the match set is a subset. `category`, if given, must be one of the slugs returned by `list_categories` — call that tool first, do not guess a slug; an unrecognized slug is rejected with an error (never a silent empty `results`). `category` is additive to `query` (AND, not OR) — pass `query: ""` to browse a category without a name/domain filter. If many shops match, grouping by country or category keeps the list scannable.

  after · 83% of words in common

  Search merchants/shops by free-text query (name or domain fragment), optionally filtered by country (ISO 3166-1 alpha-2, e.g. "DE") and/or by an EXACT category slug. Returns the public shop view only — shops still under internal review are never returned. `results` carries at most `limit` entries (default 50, max 100); `total_count` is the full match count before that cap and `truncated` is true when more results exist beyond this page — raise `offset` (default 0) to page through them. Multi-word queries are matched conjunctively: every word must be evidenced on a shop (name, domain or category). `ignored_terms` lists the words that matched nothing anywhere in the corpus and were therefore dropped to avoid an empty answer — a non-empty `ignored_terms` means the results answer a NARROWER question than you asked, so do not present them as satisfying those words. `match_quality` says how well the query was evidenced: "full" (every word found as a name/domain/category fragment — this is evidence of a fragment, NOT relevance, results are not ranked), "partial" (some words are in `ignored_terms`; the results answer a narrower question), "none" (no match). For "partial" and "none", `suggestions` carries hints instead of a guess: `categories` (slugs from `list_categories`, German words like "schuhe" are mapped, retry with `category`) and `shops` (domains within typo distance, e.g. "bergzeitt" -> bergzeit.de); both are empty for "full". `category_truncated` is true when category resolution hit its internal cap and the match set is a subset. `category`, if given, must be one of the slugs returned by `list_categories` — call that tool first, do not guess a slug; an unrecognized slug is rejected with an error (never a silent empty `results`). `category` is additive to `query` (AND, not OR) — pass `query: ""` to browse a category without a name/domain filter. If many shops match, grouping by country or category keeps the list scannable.

• 2026-10-05list_couponschangeddescription, input schema
  before

  List currently USABLE discount codes/coupons, optionally filtered by shop_domain (e.g. "otto.de"). A code is withheld from `results` when it is EXPIRED (valid_until has passed), when a real checkout test PROVED it does not work (verification_status "verified_rejected"), or when a display policy suppresses it on this channel/country. Nothing is withheld silently: `total_count` is how many codes the query found before any of that, and `withheld` breaks the difference down by reason ({expired, verified_rejected, reserved_test_domain, policy}) — total_count minus results.length always equals the sum of `withheld`, and `note` states the same balance in one sentence. So an empty `results` NEVER has to be guessed at: read `total_count` and `note` to tell "this shop has no codes at all" apart from "it has codes and every one of them is proven dead". An UNKNOWN or internal-review shop_domain is a different answer again — it is an error ("shop not found"), not an empty list; and a backend failure is reported as a failure, never as an empty list. Each result carries validUntil: an ISO timestamp when the code has a stated expiry, or null when it is open-ended — null means unlimited, NOT unknown-and-expired. Re-check validUntil against the current time before relaying a code. Each result ALSO carries verificationStatus, the verdict of a real checkout test against this exact code: "verified_applied" means the code worked in an actual checkout attempt — safe to recommend (the response carries no stored proof artifact, so do not promise a screenshot or receipt); "unverified" means no proof exists either way yet — treat it as unknown, NOT as a negative signal, and do not imply it was tested and failed. ("verified_rejected" is defined as before but no longer appears in `results` — it is counted in `withheld.verified_rejected` instead.) lastVerifiedAt is the ISO timestamp of that most recent test, or null if the code was never tested. A non-null lastVerifiedAt on an "unverified" code means it WAS tested but the test was inconclusive — it is not the same as a code that was never attempted.

  after · 81% of words in common

  List currently USABLE discount codes/coupons, optionally filtered by shop_domain (e.g. "otto.de"). A code is withheld from `results` when it is EXPIRED (valid_until has passed), when a real checkout test PROVED it does not work (verification_status "verified_rejected"), or when a display policy suppresses it on this channel/country. Nothing is withheld silently: `total_count` is the REAL number of codes the query found before any of that (for the collection list the full count over everything, never just the window), `examined` is how many codes this call looked at, and `withheld` breaks the difference down by reason ({expired, verified_rejected, reserved_test_domain, policy}) — examined minus results.length always equals the sum of `withheld`, and `note` states the same balance in one sentence. WITHOUT shop_domain the call returns one window of at most `limit` codes (default 100, max 100) starting at `offset` (default 0), ordered by a stable id: `truncated` is true when more codes lie beyond it and `next_offset` is the offset to pass for the next page (null on the last page) — page until `truncated` is false to see every code. limit/offset are rejected together with shop_domain, which already returns every code of that shop. So an empty `results` NEVER has to be guessed at: read `total_count` and `note` to tell "this shop has no codes at all" apart from "it has codes and every one of them is proven dead". An UNKNOWN or internal-review shop_domain is a different answer again — it is an error ("shop not found"), not an empty list; and a backend failure is reported as a failure, never as an empty list. Each result carries validUntil: an ISO timestamp when the code has a stated expiry, or null when it is open-ended — null means unlimited, NOT unknown-and-expired. Re-check validUntil against the current time before relaying a code. Each result ALSO carries verificationStatus, the verdict of a real checkout test against this exact code: "verified_applied" means the code worked in an actual checkout attempt — safe to recommend (the response carries no stored proof artifact, so do not promise a screenshot or receipt); "unverified" means no proof exists either way yet — treat it as unknown, NOT as a negative signal, and do not imply it was tested and failed. ("verified_rejected" is defined as before but no longer appears in `results` — it is counted in `withheld.verified_rejected` instead.) lastVerifiedAt is the ISO timestamp of that most recent test, or null if the code was never tested. A non-null lastVerifiedAt on an "unverified" code means it WAS tested but the test was inconclusive — it is not the same as a code that was never attempted.

• 2026-10-04list_couponschangeddescription
  before

  List currently USABLE discount codes/coupons, optionally filtered by shop_domain (e.g. "otto.de"). A code is withheld from `results` when it is EXPIRED (valid_until has passed), when a real checkout test PROVED it does not work (verification_status "verified_rejected"), or when a display policy suppresses it on this channel/country. Nothing is withheld silently: `total_count` is how many codes the query found before any of that, and `withheld` breaks the difference down by reason ({expired, verified_rejected, reserved_test_domain, policy}) — total_count minus results.length always equals the sum of `withheld`, and `note` states the same balance in one sentence. So an empty `results` NEVER has to be guessed at: read `total_count` and `note` to tell "this shop has no codes at all" apart from "it has codes and every one of them is proven dead". An UNKNOWN or internal-review shop_domain is a different answer again — it is an error ("shop not found"), not an empty list; and a backend failure is reported as a failure, never as an empty list. Each result carries validUntil: an ISO timestamp when the code has a stated expiry, or null when it is open-ended — null means unlimited, NOT unknown-and-expired. Re-check validUntil against the current time before relaying a code. Each result ALSO carries verificationStatus, the verdict of a real checkout test against this exact code: "verified_applied" means the code was proven to work by an actual checkout attempt with proof on file — safe to recommend; "unverified" means no proof exists either way yet — treat it as unknown, NOT as a negative signal, and do not imply it was tested and failed. ("verified_rejected" is defined as before but no longer appears in `results` — it is counted in `withheld.verified_rejected` instead.) lastVerifiedAt is the ISO timestamp of that most recent test, or null if the code was never tested. A non-null lastVerifiedAt on an "unverified" code means it WAS tested but the test was inconclusive — it is not the same as a code that was never attempted.

  after · 95% of words in common

  List currently USABLE discount codes/coupons, optionally filtered by shop_domain (e.g. "otto.de"). A code is withheld from `results` when it is EXPIRED (valid_until has passed), when a real checkout test PROVED it does not work (verification_status "verified_rejected"), or when a display policy suppresses it on this channel/country. Nothing is withheld silently: `total_count` is how many codes the query found before any of that, and `withheld` breaks the difference down by reason ({expired, verified_rejected, reserved_test_domain, policy}) — total_count minus results.length always equals the sum of `withheld`, and `note` states the same balance in one sentence. So an empty `results` NEVER has to be guessed at: read `total_count` and `note` to tell "this shop has no codes at all" apart from "it has codes and every one of them is proven dead". An UNKNOWN or internal-review shop_domain is a different answer again — it is an error ("shop not found"), not an empty list; and a backend failure is reported as a failure, never as an empty list. Each result carries validUntil: an ISO timestamp when the code has a stated expiry, or null when it is open-ended — null means unlimited, NOT unknown-and-expired. Re-check validUntil against the current time before relaying a code. Each result ALSO carries verificationStatus, the verdict of a real checkout test against this exact code: "verified_applied" means the code worked in an actual checkout attempt — safe to recommend (the response carries no stored proof artifact, so do not promise a screenshot or receipt); "unverified" means no proof exists either way yet — treat it as unknown, NOT as a negative signal, and do not imply it was tested and failed. ("verified_rejected" is defined as before but no longer appears in `results` — it is counted in `withheld.verified_rejected` instead.) lastVerifiedAt is the ISO timestamp of that most recent test, or null if the code was never tested. A non-null lastVerifiedAt on an "unverified" code means it WAS tested but the test was inconclusive — it is not the same as a code that was never attempted.

Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.