Skip to main content
Glama

LUMA NBA Impact Metrics

game_ratings

Read-onlyIdempotent

LUMA game ratings (the lumahoops.org/games page): every NBA regular-season game of 2025-26 and 2026-27, each player's Game ARC (points he added to his team's margin vs an average player in the same possessions), Game ARC per 100 possessions, the four ARC channels (shot value offense / defense, possession value gained / retained), the 0-10 game rating (6.6 = a typical game), PAC and his box score. level: players (default) or teams (team totals, average rating, channels). Filters: date (YYYY-MM-DD, or "latest" = the latest rated day; the default when no other filter is given), from, to, game_id, team, player (name), min_minutes. decomposition: true (players level) adds the full Game ARC decomposition: each channel split into its counted parts, shot parts by zone (rim, paint, mid, three) and free throws, attempts and makes per zone, plus one lineup number per channel; parts + lineup = the channel. Updated daily. Up to 5,000 rows per call; use offset for more.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "game_ratings"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNo
dateNo
fromNo
teamNo
levelNo
limitNo
offsetNo
playerNo
game_idNo
min_minutesNo
decompositionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare a read-only, idempotent, closed-world, non-destructive operation, so the safety profile is covered. The description adds genuinely useful operational context beyond that: daily refresh cadence, a 5,000-row per-call cap, offset paging, and the 'latest' default resolution rule.

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?

A single dense block, but front-loaded: what the data is first, then level, then filters, then decomposition, then operational notes. Every clause carries information, though the decomposition sentence is long and undefined acronyms (PAC) slow scanning slightly.

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?

For an 11-parameter read tool with no output schema, the description covers the returned fields (Game ARC, per-100, four channels, 0-10 rating with 6.6 as a typical game, PAC, box score), the season scope, filtering, and pagination. An agent can call this correctly and interpret results without further documentation.

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

Parameters4/5

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

With 0% schema description coverage across 11 parameters, the description carries the whole burden and largely succeeds: it explains date format plus the 'latest' sentinel, from/to, game_id, team, player, min_minutes, level semantics (players default vs team totals/averages/channels), and that decomposition only applies at player level. Only limit and offset semantics (beyond 'use offset for more') are left thin.

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

Purpose4/5

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

The description identifies the resource precisely: per-game Game ARC ratings for every NBA regular-season game in 2025-26 and 2026-27, at player or team level. It even names the source page, so an agent knows exactly what data it gets. It stops short of a clean verb framing and never contrasts itself with siblings like game_log or leaderboard.

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

Usage Guidelines3/5

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

Usage is implied rather than stated: date defaults to 'latest' when no filter is given, and offset is named as the way to page beyond 5,000 rows. There is no explicit when-to-use-this-vs-alternatives guidance, so an agent must infer that game_log or leaderboard serve different purposes.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources