Skip to main content
Glama

Prop Correlations: What Moves Together

correlations
Read-onlyIdempotent

Use this when the user asks which players' stat lines tend to go over or under together in a game, or who a player's outcomes move with (teammates and opponents). Returns, for a game_id, its typical role pairs (typical: the phi and lifts of the players' roles, pooled over earlier seasons) and the game-script splits (script: the roles' over rates on tonight's side of the spread and total); for a player_id, his partners in his next game (partners). Counted over the games both played, before the game asked. With Keel Stats Pro also each pair's own sample (joint counts, lift, phi shrunk to its role pair) and the pairs ranked on their samples (pairs); account.held says when they were left out. A pair's past season does not predict its next well. Not for a player's own lines: use props_research.

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>"
    },
    "name": "correlations"
  }
}

Input Schema

NameRequiredDescriptionDefault
statNoOptional, with a player_id: his stat to pair (NBA: "pts", "reb", "ast", "tpm"…; NFL: "receiving_yards", "rushing_yards"…).
leagueYesLeague ("nba" or "nfl").
game_idNoNumeric game ID (from tonight_slate or find_game): the game's pairs.
player_idNoNumeric player ID (from search): his partners. Ignored with a game_id.

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?

Annotations already establish that this is a safe, idempotent, closed-world read, so the description earns credit for what it adds: the data window ('Counted over the games both played, before the game asked'), tier gating ('With Keel Stats Pro also...'; '`account.held` says when they were left out'), and an honest predictive caveat ('A pair's past season does not predict its next well'). The return-key breakdown (typical/script/partners/pairs) tells the agent how to interpret results, which annotations cannot.

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?

Front-loaded with the use case, then the return contract, then the caveat and the redirect – a sensible order with no filler sentences. It is dense and jargon-heavy ('the phi and lifts of the players' roles', 'lift, phi shrunk to its role pair') with semicolon-chained clauses that slow parsing, though no sentence is wasted.

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?

No output schema exists, so the description must carry the return contract, and it does: it names each response bucket (`typical`, `script`, `partners`, `pairs`) and flags the tier-gated fields. It also qualifies the temporal basis of the data and the reliability limit, which is everything an agent needs to call and interpret this correctly.

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, but the description adds genuinely useful semantics beyond the schema by mapping each parameter to a distinct output shape (game_id yields pooled role pairs plus game-script splits; player_id yields next-game partners) and by clarifying that `stat` only matters alongside a player_id. The overlap with the schema's own 'Ignored with a game_id' note keeps it from being fully additive.

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?

States a concrete verb-and-resource purpose ('which players' stat lines tend to go over or under together') and enumerates exactly what it returns for each input mode: `typical`/`script` for a game_id, `partners` for a player_id. It explicitly names the sibling it is not (props_research), so an agent can separate it from the adjacent tools without reading either 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?

Opens with an explicit use-when clause ('Use this when the user asks which players' stat lines tend to go over or under together... or who a player's outcomes move with') and closes with an explicit exclusion plus the correct alternative ('Not for a player's own lines: use props_research'). Both the positive trigger and the redirect are stated, leaving nothing to infer.

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