Skip to main content
Glama

Game Projection & Matchup Breakdown

game_projection
Read-onlyIdempotent

Use this when the user asks who is favoured in one game, by how much, or how the two sides compare for it. Returns the pre-game win probability (NBA: our projection, blended with the market while the model learns; prediction.blended says when) and projected margin, the consensus spread and total, the teams compared, leaders, recent form and who is out; signed in, also the market's vig-free chance, the model against it and the line, and the head-to-head; with Keel Stats Pro the absence costs, position matchups, records against the close and key players, and with a Pro account detail "full" adds the model's factor weights (below Pro it answers the same as "compact", with projection_detail in account.held, so leave it unset unless the caller has Pro). The answer's account.held names what the caller's plan left out. Needs a game_id from tonight_slate or find_game. Not for picks or betting advice: Keel Stats gives neither.

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": {
      "league": "<league>",
      "game_id": "<game_id>"
    },
    "name": "game_projection"
  }
}

Input Schema

NameRequiredDescriptionDefault
detailNo"compact" (default) or "full": with Keel Stats Pro adds the model's factor weights and strengths; below Pro the compact answer, with `projection_detail` held.
leagueYesLeague ("nba" or "nfl").
game_idYesNumeric game ID (from tonight_slate, find_game or team_profile).
include_breakdownNoOlder form of detail "full": true adds the model factor weights with Keel Stats Pro; below Pro the compact answer, with `projection_detail` held.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / detail / description
      Previous value: -"\"compact\" (default) or \"full\" (Keel Stats Pro): adds the model's factor weights and strengths."New value: +"\"compact\" (default) or \"full\": with Keel Stats Pro adds the model's factor weights and strengths; below Pro the compact answer, with `projection_detail` held."
    • changedInput schema / properties / include_breakdown / description
      Previous value: -"Older form of detail \"full\": true adds the model factor weights (requires Keel Stats Pro)."New value: +"Older form of detail \"full\": true adds the model factor weights with Keel Stats Pro; below Pro the compact answer, with `projection_detail` held."
  2. Changed2 schema fields changed
    • addedInput schema / properties / detail
      Added value: +{
      +  "description": "\"compact\" (default) or \"full\" (Keel Stats Pro): adds the model's factor weights and strengths.",
      +  "enum": [
      +    "compact",
      +    "full"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / include_breakdown / description
      Previous value: -"Set true (requires Keel Stats Pro) to include model factor weights, player absence costs, position matchups, and ATS records. Defaults to true when signed in with Pro."New value: +"Older form of detail \"full\": true adds the model factor weights (requires Keel Stats Pro)."
  3. Changed1 schema field changed
    • changedInput schema / properties / game_id / description
      Previous value: -"Numeric game ID (from tonight_slate or team_profile)."New value: +"Numeric game ID (from tonight_slate, find_game or team_profile)."
  4. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare this a safe, idempotent read; the description goes far beyond by disclosing tiered output gating — what signed-in users get, what Keel Stats Pro adds, and that `detail: full` degrades to compact below Pro with `projection_detail` listed in `account.held`. It also explains that `account.held` is the authoritative list of withheld data, which is exactly the kind of behavior an agent needs to interpret a partial response.

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 intent and prerequisite are front-loaded and every clause carries information — nothing is filler. The downside is structure: the tiered-output detail is delivered as one long semicolon chain inside a single sentence, which is harder to parse than a short bulleted breakdown would be.

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?

There is no output schema, so the description must describe returns, and it does so thoroughly: probability, margin, spread/total, comparison fields, and the plan-gated extras. Prerequisites, entitlement behavior, and the withheld-data signal are all covered, leaving no obvious gap for a correctly-formed call.

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 baseline is 3; the description adds genuine meaning by explaining the consequence of `detail: full` under different entitlements and advising the caller to omit it when not on Pro. It also tells the caller where a valid `game_id` comes from, though `include_breakdown` is left to the schema.

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 opening states a specific user intent ('who is favoured in one game, by how much, or how the two sides compare') and enumerates concrete outputs: pre-game win probability, projected margin, consensus spread and total, leaders, recent form, injuries. It also carves out scope ('Not for picks or betting advice'), so an agent can separate this from props_research or line_shop 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 Guidelines4/5

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

Clear when-to-use framing plus an explicit exclusion for picks/betting advice and a prerequisite ('Needs a game_id from tonight_slate or find_game'). It also gives a decision rule for `detail` (leave unset unless the caller has Pro). It does not, however, name sibling alternatives for adjacent questions such as head_to_head or line_history.

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