Skip to main content
Glama
DanielTomaro13

sportsdata-mcp

by DanielTomaro13
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

nbl_match_boxscore

Read-onlyIdempotent

Retrieve one NBL game's full box score: final score, player stat lines, and team totals by quarter. Get the match ID from nbl_schedule first.

Instructions

One game's box score: final score, every player's line (minutes, points, rebounds, assists, shooting splits including four-pointers, +/-, efficiency) and team totals by quarter. Get the match id from nbl_schedule (data[].id).

Returns: {type, count, data:[{id, match_title, start_time, status, home_score, away_score, venue:{name}, home_team:{id, name, team_code}, away_team:{…}, boxscore_field_mapping:{points:'PTS', …}, player_match_statistics:[{player:{full_name, jersey_number, playing_position}, team:{team_code}, period:'0', starter, participated, minutes:'24:30', points, rebounds, assists, …}], team_match_statistics:[{team:{team_code}, period:'0'|'1'…'4', points, rebounds, …}]}]} — data is a one-element list. TEAM rows are per quarter: period '0' is the full game and '1'-'4' the quarters, so filter on period before summing or you count every point twice. Player rows are full-game (period '0'). The NBL has four-point shots, hence the four_points_* columns. Check participated to skip players who did not play. TYPES: the header's home_score/away_score are STRINGS ('86'), while every stat is a number, and percentages are fractions (0.4 = 40%), so convert before comparing a stat to the score.

Example: Tasmania JackJumpers v NZ Breakers, NBL Blitz, 6 Sep 2026 {"matchId": "3d09795f-58a7-11f1-aed3-b7a799a5060e"}

Auth: none needed.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
matchIdYesMatch UUID from nbl_schedule (data[].id). Required — part of the URL path.

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 only cover the safe-read profile (readOnly/idempotent/openWorld), but the description goes far beyond by disclosing non-obvious behavioral traps: team rows are duplicated across period '0'-'4' and summing without filtering double-counts, player rows are full-game only, the NBL has four-point columns, and the 'participated' flag should gate players. It also states auth is not needed.

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 content is dense and front-loaded: purpose first, then a full return-shape sketch, then the critical period/type caveats. Every section carries real information (the double-counting and string-vs-number warnings are high value), though the long inline return schema is somewhat redundant given the structured response contract.

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 must shoulder return-value disclosure, and it does so thoroughly: field-by-field shape, the one-element data list, period semantics for team vs player rows, and type quirks (scores as strings, percentages as fractions). An agent has everything needed to call and interpret the response correctly.

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 coverage is 100% and the schema itself already documents that matchId is a required UUID sourced from nbl_schedule (data[].id) and used in the URL path. The description repeats this provenance but adds no format, validation, or edge-case detail beyond the schema, 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?

States a specific verb+resource ('One game's box score') and enumerates exactly what it contains: final score, per-player lines, team totals by quarter. This clearly distinguishes it from siblings like nbl_match_playbyplay (event-level) and nbl_player_boxscores (player-scoped), and it names the schedule tool that supplies the id.

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 explicitly tells the agent how to obtain the required input ('Get the match id from nbl_schedule (data[].id)'), which is the key precondition. It doesn't spell out when NOT to use it versus the sibling boxscore/playbyplay tools, so it stops short of full routing guidance.

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