Skip to main content
Glama

Tonight's Minutes & Expected Stats

stat_forecasts
Read-onlyIdempotent

Use this when the user asks how many minutes an NBA player should play tonight, who gets more minutes or shots when a teammate is out, or what a player is expected to score, rebound and assist tonight. Returns tonight's games with each team's players: the minutes they have been playing, the minutes expected after the injury report and how much the absences move them, usage, who is out and the minutes he frees; with Keel Stats Pro also expected points, rebounds and assists, the chances of reaching a number, the team both ways around each player in doubt, and with a player_id who gained when he sat. Over a whole slate each team's top seven come as one compact table (minutes, expected, the absences' move, Pro's expected points, rebounds and assists); a game_id, team_id or player_id gives the full rows. account.held names what the caller's plan left out. Not for past games: use player_profile.

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": "stat_forecasts"
  }
}

Input Schema

NameRequiredDescriptionDefault
leagueNoLeague: "nba" (the NFL has no minutes model).nba
game_idNoOptional numeric game ID from tonight_slate: that game alone.
team_idNoOptional numeric team ID from search: that team's side alone.
player_idNoOptional numeric player ID from search: his team tonight, and who gained when he sat.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the readOnly/idempotent annotations, the description discloses call-shape behavior: a bare slate call returns a compact top-seven table, while a game_id, team_id or player_id expands to full rows, and `account.held` reports what the caller's plan omitted. That plan-gating and aggregation behavior is context the annotations cannot convey.

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?

Usage guidance is front-loaded and the final sentence routes to the sibling, but the middle sentences are long run-ons that pack many features into single clauses. It is dense and readable rather than wasteful, though a bulleted structure would scan faster.

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 return-shape burden and does so: it specifies the aggregate vs full-row formats, names the columns in the compact table, and flags plan-gated fields. Nothing essential for calling or interpreting the result is missing.

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 3 is the floor, and the description earns above that by explaining the output difference across parameter combinations (whole slate → compact table; any ID → full rows). The per-parameter glosses largely echo the schema wording, so it stops short of adding independent syntax or format detail.

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 names a specific resource (tonight's minutes and expected stats) and enumerates exactly what comes back: minutes played, expected minutes after the injury report, usage, absences, and Pro-level expected points/rebounds/assists. It also explicitly separates itself from player_profile for past games, so an agent can route correctly without opening the 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?

The opening sentence lists concrete user questions that should select this tool (minutes tonight, who gains when a teammate is out, expected scoring line), and the closing sentence states an explicit exclusion with the named alternative: 'Not for past games: use player_profile.' Both the when and the when-not are covered.

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