Skip to main content
Glama

Most Often Guarded By & Defensive Assignments

player_matchups
Read-onlyIdempotent

Use this when the user asks who guards an NBA player most often, how a player scored against a given defender, or whom a defender was matched up on and how those players scored against him. Returns, for a player_id and a season (2020-21 on), his most frequent defenders and, as a defender, the players he guarded most, each pair as season sums: games, minutes matched, share of his matched time, points, points per 100 possessions and the difference from the scorer's own rate (only from five matched minutes), field goals and threes made and attempted; last season beside it early in a season. Not for how a team defends a position: use defense_vs_position; not for his own averages: use player_profile.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "player_id": "<player_id>"
    },
    "name": "player_matchups"
  }
}

Input Schema

NameRequiredDescriptionDefault
leagueNoLeague: "nba" (defensive matchups are tracked for the NBA).nba
seasonNoOptional season year (2026 = 2025-26; from 2021). Defaults to the current season.
player_idYesNumeric player ID from search.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already establish read-only, idempotent, closed-world behavior, and the description goes further by disclosing the five-matched-minute inclusion threshold, the 'last season beside it early in a season' fallback, and the exact metric list including the difference-from-own-rate stat. It does not say what happens for a player with no tracked matchups or whether an invalid/earlier season errors, which keeps it short of a 5.

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 usage trigger and the negative routing are front-loaded, and every clause carries content — thresholds, season range, metric list. The middle sentence is a long semicolon-chained run-on that takes effort to parse, which is the main deduction.

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 carries the full burden of explaining returns and does so thoroughly: the pair structure, the season-sum nature of each field, the five-minute filter, and the previous-season comparison behavior. Combined with a 100%-documented schema and read-only annotations, an agent has everything needed to call it correctly.

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?

Schema coverage is 100%, so the parameter definitions already do the baseline work, but the description adds real meaning: the season range is restated as '2020-21 on' and player_id is tied to the dual output interpretation (his defenders, and his assignments as a defender). The league parameter is left entirely to the schema, which is fine given its single enum value.

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 precise statement of what questions the tool answers ('who guards an NBA player most often', 'how a player scored against a given defender', 'whom a defender was matched up on') and immediately follows with the concrete return shape: defender/guarded pairs as season sums. It is unmistakably distinct from player_profile or defense_vs_position, so an agent can pick it without opening a schema.

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

Usage Guidelines5/5

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

It gives both positive triggers (the three user-question phrasings) and explicit exclusions with named alternatives: 'Not for how a team defends a position: use defense_vs_position; not for his own averages: use player_profile.' Both the when and the when-not are stated, so routing is unambiguous.

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