Skip to main content
Glama
DanielTomaro13

sportsdata-mcp

puntersedge_racing_results

Read-onlyIdempotent

Retrieve settled AU/NZ racing results with finishing order, fixed prices, starting prices, dividends, scratchings and deductions for horses, greyhounds and harness.

Instructions

Settled AU/NZ results: finishing order, each bookmaker's settled fixed price, starting prices, dividends, scratchings and their deductions. Costs 2 credits.

Returns: [{race_id, venue, venue_canonical, race_number, category, country, start_time, race_name, distance_m, track_condition, going, status:'final'|'interim'|'abandoned', status_note, field_status, placings:[{name, number, position, win_price, place_price, sp, sp_note}], runners:[{name, number, position, status:'ran'|'scratched'|'late_scratching'|'reserve', dead_heat, jockey, trainer, sp, margin, time_s, abnormal, runner_ref}], deductions, dividends, resulted_at}] (top-level ARRAY). A runners entry is NOT necessarily a starter — read its status. A scratched runner can still carry an sp, and that price is NOT what its deduction was struck from: take the deduction from deductions, never from 1/sp.

NOTE: this shape is from the vendor's documentation and has NOT been verified against a live response (we hold no key for this provider). Treat it as approximate — inspect the actual payload before relying on a field name.

Example: Yesterday's settled AU thoroughbred results {"hours_back": 24, "categories": "horse", "country": "AU", "status": "final"}

Auth: needs your own key in PUNTERSEDGE_API_KEY.

Also answers this: pointsbet_racing_race, sportsbet_racing_resulted_events, tab_racing_race.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dateNoSingle-day alias, YYYY-MM-DD, returning that AET meeting date instead of a rolling window. Mutually exclusive with hours_back.
limitNoRaces to return.
venueNoVenue name, case-insensitive, e.g. Rosehill.
offsetNoRows to skip, for paging.
statusNoFilter by settlement status. Settle only against `final` — an `interim` placing can still change on protest, and becomes final once placings have been stable for 30 minutes.
countryNoComma-separated ISO country codes, case-insensitive, e.g. AU or AU,NZ. A result whose country was never resolved is EXCLUDED by any value here, so omit the filter if you need those.
categoriesNoComma-separated racing codes: horse, greyhound, harness. Omit for all.
hours_backNoHow far back to look, in hours, up to 7 days. Mutually exclusive with `date`.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.33.0

TDQS

A4.4/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, openWorld), yet the description adds substantial behavioral context: the 2-credit cost, the requirement for a PUNTERSEDGE_API_KEY, the vendor-doc/unverified caveat, and critical data quirks (runners may be scratched, a scratched runner's sp is not the deduction basis, take it from `deductions`). That is exactly the value-add beyond structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening line is tightly front-loaded, but the verbose inline return-shape listing is dense. It earns its place because no output schema exists, though it could be tightened; overall the structure is logical and signal-dense.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description compensates by enumerating the return shape, field semantics, and status meanings, plus auth and cost. For an 8-parameter, no-required-arg read tool, nothing an agent needs to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all eight parameters are already documented in the schema, including the `date`/`hours_back` mutual exclusion and the `status` and `country` semantics. The description reinforces with an example but adds no new parameter-level meaning, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb+resource+scope: 'Settled AU/NZ results' and enumerates exactly what is returned (finishing order, settled fixed price, starting prices, dividends, scratchings/deductions). An agent can immediately distinguish it from siblings like puntersedge_racing_next_to_go or puntersedge_racing_events.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives concrete usage context via the example query and the status guidance ('Settle only against `final` — an `interim` placing can still change on protest'), and names overlapping siblings ('Also answers this: pointsbet_racing_race, sportsbet_racing_resulted_events, tab_racing_race'). It stops short of explicitly telling the agent when to prefer it over puntersedge_racing_closing_lines or the movers tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools