Crawlora MCP

Official

Overview Schema Source Related Servers Discussions Admin

nba_team_stats_leaders

Retrieve NBA league leaders for a chosen statistical category, such as points, rebounds, or assists, with optional season and per-game or totals filters.

Instructions

NBA league leaders for one statistical category. Returns the league leaders table for one ranked statistical category: one row per player with the columns the source publishes, keyed by the source's own column names such as PLAYER_ID, PLAYER_NAME, TEAM_ID, GP, MIN, PTS, REB and AST. stat_category is required and only the verified categories are accepted; the upstream answers HTTP 403 when it is omitted, so this route rejects the request locally instead.

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": {
      "stat_category": "<stat_category>"
    },
    "name": "nba_team_stats_leaders"
  }
}

Input Schema

Name	Required	Description
`scope`	No	Player-pool scope; S is all players (the only verified value)
`season`	No	Season in YYYY-YY form; defaults to the current NBA season
`per_mode`	No	Aggregation; PerGame or Totals
`league_id`	No	League id; only 00 (NBA) is verified
`season_type`	No	Season type; Regular Season or Playoffs
`stat_category`	Yes	Ranked statistic; PTS, REB or AST

Schema Changelog

Changes observed during successful MCP inspections.

Addedv1.17.20Nov 12, 2026

TDQS

A3.7/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and mostly discharges it: it discloses the row cardinality (one per player), the column naming convention from the upstream source, and a concrete failure mode — upstream HTTP 403 on missing category, rejected locally instead. It omits pagination, rate limits, and result-size bounds, which keeps it out of the top score.

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?

Two sentences, front-loaded with the tool's identity before the return-shape detail. There is mild redundancy between 'for one statistical category' and 'for one ranked statistical category', but every other clause carries information an agent needs.

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 six-parameter read tool with no output schema and no annotations, the description covers purpose, row shape, column naming, and error behavior — enough to call it correctly. The remaining gap is that it never says what the optional parameters do at a conceptual level, leaving the agent dependent on the schema.

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% with enums on five of six parameters, so the schema already explains each field's domain. The description adds only that stat_category is strictly required and restricted to verified values, plus the error consequence of omitting it; it says nothing about season, per_mode, or scope semantics, so the 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 gives a specific verb and resource ('league leaders table for one ranked statistical category') and clarifies granularity as 'one row per player', which implicitly separates it from the team-level siblings. It stops short of naming any sibling tool such as nba_team_stats or nba_homepage_leaders, so an agent must infer the differentiation.

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 context is implied through the required stat_category and the note that only verified categories are accepted, which tells the agent this is a single-category lookup. There is no explicit when-to-use statement, no excluded cases, and no named alternative for adjacent needs (e.g., team-level leaders or per-player career totals).

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

Deploy Server