SiteCheck Agent Intel & Dev

NBA player season statistics, sorted leaderboard: per

dev_nba_stats

Read-only

NBA player season statistics, sorted leaderboard: per player team, position, age, games, minutes, points, rebounds, assists, steals, blocks, turnovers, FG/3P/FT made-attempted-percentage, double-doubles, triple-doubles (per-game and totals). Regular season or playoffs, 2003 to now (season = year it ends, 2026 = 2025-26). Data from ESPN's public stats API (stats.nba.com blocks automated access). Related tools on this server, for a different need: dev_wnba_stats when you need WNBA player season statistics, sorted leaderboard: per; dev_mlb_stats when you need MLB player season stats and bio from the official MLB Stats. Price: $0.002 in USDC per successful call, paid with x402 (Base, Solana or Arc); failed calls are not charged.

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": "dev_nba_stats"
  }
}

Input Schema

Name	Required	Description
`page`	No	Page, 1 to 40
`sort`	No	points, rebounds, assists, steals, blocks, threes, fgpct, minutes
`limit`	No	Players per page, 1 to 50 (default 25)
`season`	No	Season end year, e.g. 2026 for 2025-26 (default current)
`seasonType`	No	regular (default) or playoffs
`qualifiedOnly`	No	true (default) = only players meeting ESPN's minimums

Output Schema

Name	Required	Description	Default
`page`	No
`sort`	No
`season`	No
`source`	No
`results`	No
`checkedAt`	No
`seasonType`	No
`seasonLabel`	No
`totalPlayers`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations only declare readOnlyHint and openWorldHint; the description adds genuinely non-obvious behavior: data provenance (ESPN public stats API, with the note that stats.nba.com blocks automated access), historical coverage (2003 to now), and season-year convention. It also discloses the paid x402 billing model at $0.002 per successful call with failed calls not charged — material for an agent deciding whether to call. It stops short of describing rate limits, pagination behavior, or response shape (mitigated by the existing output schema).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening stat enumeration is efficient and front-loaded, but the sibling referral is padded with repetitive template phrasing ('Related tools on this server, for a different need: ... when you need WNBA player season statistics, sorted leaderboard: per') that echoes the title verbatim. The pricing sentence is long but each clause (price, rail, failure policy) carries distinct meaning.

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-optional-parameter read tool with a full schema, complete annotation coverage, and an output schema, the description supplies what structured fields can't: provenance, temporal coverage, and cost. The main residual gap is pagination/result-volume expectations, though page and limit are bounded in the schema.

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 description coverage is 100%, so the baseline is 3, but the description adds two pieces of meaning beyond the schema: the valid temporal range for `season` (2003 to now) and the description's own restatement of the season-end-year convention. It still doesn't clarify sort ordering direction (asc/desc) or the relationship between page/limit and the 40-page cap beyond what the schema states.

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 names a specific resource and scope: NBA player season stat leaderboards, enumerating the exact stat columns returned (points, rebounds, assists, FG/3P/FT splits, double/triple-doubles) plus per-game vs totals granularity. It also explicitly separates itself from dev_wnba_stats and dev_mlb_stats, so an agent can discriminate it from the nearest siblings. It lacks a leading verb ('Get/List') but the resource is unambiguous.

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 gives clear routing guidance by naming two alternatives and the need each serves ('dev_wnba_stats when you need WNBA...', 'dev_mlb_stats when you need MLB...'). It does not address other plausible confusions on this crowded sports server, e.g. dev_espn_nba_scoreboard (game-level results) or dev_nfl_stats, nor does it state an explicit when-not-to-use condition.

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

All SiteCheck Agent Intel & Dev tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?