nempulse

Quality 72 / 100needs work

11 tools, about 4,043 tokens to load them all · tool set 77523ac440e7 · tools last changed 2026-10-04 · checked 2026-10-20 12:45 UTC

Tool changes

• 2026-10-04get_rankingsadded

  League table of merchant NEM batteries over a date range, ranked by capture rate by default (actual revenue as a share of the forecast-informed benchmark; capture_perfect_pct is the share of the perfect-foresight ceiling). Each row has rank, duid, station, region, capacity, duration_band, capture_fc_pct, capture_perfect_pct, rev_per_mw_day, rev_per_mwh_day, total_rev, cycles_per_day and movement against the previous period of equal length. Units still commissioning and CONTRACTED or TOLLED units are listed under excluded, not ranked, unless include_arrangement is true (their spot revenue is not their commercial return). Check unit_class and peer_comparable before reading a gap as performance. It scans the whole fleet twice, so keep the range to a month or less; it can be slow or time out on long ranges. For one unit's revenue use get_battery_revenue.

• 2026-10-04get_simulator_revenueadded

  Modelled revenue for a hypothetical 1 MW battery of a given duration in one region (not a real unit), from NEMPulse's optimal-dispatch model on real prices. Returns P10/P50/P90 revenue for three tiers: realistic (forecast-informed result scaled by the capture ratio real batteries achieve, the only tier to use as a project case), forecast_informed (idealised execution on AEMO's public price forecast) and perfect (an unreachable ceiling). Also energy_share and fcas_share, a monthly series, and the real-unit cohorts behind the FCAS cap and the capture ratio. Gross spot revenue only, before costs, degradation and financing. It is a screening estimate, not a forecast of future revenue.

• 2026-10-04get_regional_pricesadded

  Daily minimum, maximum and mean regional reference price (RRP, $/MWh) for one NEM region over a date range. Daily summary only: the raw 5-minute price series is not exposed (it is published by AEMO on NEMWEB). Use it for price context around revenue or events. For individual price spikes use list_events.

• 2026-10-04get_event_detailchangedtitle, description, input schema, annotationsmeaning changed
  before

  Summary stats for one market price event by id (per-interval dispatch during the event is not exposed).

  after · 15% of words in common

  One price event by event_id (take the id from list_events), with the response of every battery that was online, ranked by est_revenue. Event fields are as in list_events. Each battery row has duid, station, region, response (DISCH = discharging, CHRG = charging, IDLE, OFFLINE = no availability), avg_mw (positive is discharge), peak_mw, est_revenue (energy only, sum of MW times price over the event, gross, not MLF-adjusted; excludes FCAS), soc_pct at start and soc_pct_end, availability_mw, fcas_mw (average FCAS commitment), plus is_commissioning, unit_class and peer_comparable. Check those labels before comparing units. Per-interval dispatch during the event is not exposed.

• 2026-10-04list_eventschangedtitle, description, input schema, annotationsmeaning changed
  before

  List NEM spot-price events (negative, elevated, spike, extreme), optionally filtered by region.

  after · 12% of words in common

  List NEM spot-price events, newest first. An event is a run of 5-minute intervals in one region where the price stays above $500/MWh or below -$200/MWh (short gaps are bridged), typed by its peak price: negative (below -$200), elevated (peak $500 to $1,000), spike ($1,000 to $5,000) or extreme ($5,000 and above). Each event has event_id, region, event_type, started_at, ended_at, duration_min, peak_rrp, avg_rrp and is_open (still ongoing). Filter by region, event_type and a date range. By default only event summaries are returned; set include_responses to true to also get how each battery behaved during each event, in which case keep limit small (response rows make the payload large and it is truncated at about 100 KB). Use get_event_detail for one event's battery responses.

• 2026-10-04get_battery_optimalchangedtitle, input schema, annotations
• 2026-10-04get_battery_revenuechangedtitle, input schema, annotations
• 2026-10-04query_nem_datachangedtitle, description, input schema, annotationsmeaning changed
  before

  Ask a natural-language question about NEM BESS data; returns generated SQL, result rows and a plain-English explanation. Scope each question to roughly one region-month or less — aggregates spanning more (e.g. a full year by region, or per-day top-N across all regions) risk the generated SQL exceeding its own 8s execution cap, which this tool's longer timeout does not extend. For per-day top-N / bottom-N questions, phrase them so the generated SQL uses a window function (ROW_NUMBER/RANK) rather than a per-day correlated subquery — the latter has been observed to silently return all-null rows with no error. Only dispatch_prices, daily_revenue, optimal_dispatch, bess_price_profile and market_events are reachable here; the market_* cache tables (market_monthly, market_regression, market_corr_tracker, market_daily_price, market_daily_fleet) behind the market-analysis page live in a separate database and are NOT queryable through this tool — a question about them will be recomputed from dispatch_prices instead, which is slower and easy to phrase incorrectly.

  after · 47% of words in common

  Last resort for ad hoc questions the other tools cannot answer. Takes a plain-English question, generates SQL over NEMPulse's tables, and returns the SQL, the result rows and a short explanation. It is the slowest tool (can take close to a minute) and it is AI-generated, so check the returned SQL before relying on a number. Scope each question to about one region-month or less: wider aggregates (a full year by region, or per-day top-N across all regions) risk exceeding the 8 second SQL limit, and a longer wait does not help. For per-day top-N or bottom-N questions, ask for a window function (ROW_NUMBER or RANK) rather than a per-day subquery, which has been seen to silently return all-null rows. Queryable data: dispatch prices, daily revenue, optimal dispatch, battery price profiles and market events. The market analysis tables (monthly spreads, regressions, correlations) are not reachable here.

• 2026-10-04get_battery_detailchangedtitle, input schema, annotations
• 2026-10-04get_fleet_summarychangedtitle, description, input schema, annotationsmeaning changed
  before

  Fleet-wide snapshot: unit count, total capacity, revenue month-to-date, average spot price.

  after · 15% of words in common

  Fleet-wide snapshot for the NEM battery fleet: unit_count, active_unit_count, total_mw, total_mwh, fleet_rev_mtd, avg_efficiency_pct, last_interval and spot_prices (latest price per region, $/MWh). Covers month-to-date unless date_from and date_to are given. fleet_rev_mtd is gross spot revenue (energy + FCAS + FPP) over that window, whatever its length, despite the name. avg_efficiency_pct is dollar-weighted actual energy revenue as a share of the perfect-foresight optimum (a capture rate), null if the optimisation has not run for the window. Commissioning units are excluded from the efficiency figure unless include_commissioning is true. For one battery use get_battery_detail; for a ranking use get_rankings.

Showing the latest 10. 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.