Skip to main content
Glama
Sign In

NBA Prop Lab

by io.github.Khavel
OverviewDiscussionsAdmin

Usage rate leaders

usage_leaders
Read-onlyIdempotent

Players ranked by explicitly observed usage percentage (0–100), not unknown/default zero values. Requires at least 10 observed qualifying games. Season and last-10 played-game observation denominators are included; missing L10 is null. Empty coverage means unavailable, not zero usage. Previous-season fallback is explicitly labelled; asOf is the query date. Minutes/points use all qualifying played games.

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": "usage_leaders"
  }
}

Input Schema

NameRequiredDescriptionDefault
leagueNoLeague: "nba" or "wnba".nba

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description is not needed for that. It still earns credit for disclosing real behavior beyond structured fields: previous-season fallback is labelled, missing L10 is null rather than zero, asOf marks the query date, and minutes/points are computed over all qualifying played games.

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 ranking definition is front-loaded, and each subsequent clause (eligibility threshold, denominators, null semantics, fallback labelling, asOf) carries distinct information. It is semicolon-dense and could be broken into shorter sentences, but there is no filler.

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

Completeness4/5

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

For a one-parameter read tool with no output schema, the description supplies the important return semantics: season and L10 observation denominators, null for missing L10, labelled previous-season fallback, and asOf. The only gap is that it does not describe the identifying fields per player (name/id) or sort direction beyond 'ranked'.

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?

There is a single 'league' parameter and schema description coverage is 100%, with the enum values listed in the schema. The description never mentions the league parameter or how it affects the denominators, so it adds nothing beyond the schema; baseline 3 applies.

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 opens with a specific verb+resource+metric: players ranked by observed usage percentage, with the scale (0-100) and the exclusion of unknown/default zeros. That is far more precise than the title alone. It does not explicitly contrast itself with siblings such as player_research or search_players, which score 5 would require.

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?

It states a data precondition (at least 10 observed qualifying games) and a caveat that empty coverage means unavailable rather than zero, which implies when results will be sparse. However, it never says when to choose this tool over player_research or search_players, so routing is left to inference.

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

All NBA Prop Lab toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources