Skip to main content
Glama

Line History, Records vs the Close & Market Report (Pro)

line_history
Read-onlyIdempotent

Use this when the user asks how a game's spread, total or moneyline opened and closed, how a player's prop lines moved and how he did against the closing line game by game, which players beat or missed their closing lines most this season, or how the sportsbooks' lines did overall (the market report). Returns, by kind: "game" (a game_id: the consensus and each book's opening and closing numbers, the vig-free market, how the game ended against the close; NFL also how many times the lines moved), "player" (a player_id: per stat his record against the close and a table of finished games with open, close, books, his number and the result, plus his next game's lines), "records" (the league's highest over and under rates against the closing prop line in a stat), "market" (the monthly market report: book margins, how closing lines missed by stat, size, position, month and move, line moves, injury reaction, with the headline numbers and editions). Requires Keel Stats Pro; the answer says so when the account has none. Not for tonight's lines and hit rates: 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": "line_history"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNo"game", "player", "records" or "market". Omit: "game" with a game_id, "player" with a player_id, else "market".
statNoOptional stat code: narrows a player's history, or picks the records' stat (NBA: "pts", "reb", "ast", "tpm", "pra"…; NFL: "passing_yards", "rushing_yards", "receiving_yards", "receptions"…).
gamesNoOptional, kind "player": finished games per stat in the table, newest first (default 10; at most 82 with a `stat`, 20 without).
leagueYesLeague ("nba" or "nfl").
seasonNoOptional season year for "records" and "market". Defaults to the season the site shows.
game_idNoNumeric game ID (from tonight_slate or find_game) for kind "game".
player_idNoNumeric player ID (from search) for kind "player".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds material context beyond that: a Keel Stats Pro entitlement gate with defined failure behavior ("the answer says so when the account has none") and a per-kind inventory of what comes back. It stops short of return format details, pagination, or the cost of the heavier `market` report, so it is strong but not exhaustive.

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 trigger condition is front-loaded in the first clause and the exclusion is placed at the end where it reads as a guard. However, the middle is a single dense enumeration of four `kind` payloads, which is hard to scan and could have been broken into per-kind lines; some of the return-field detail duplicates what the schema's `kind` description already conveys.

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 7 parameters, no output schema, and all four modes sharing one entry point, the description carries the full burden of explaining what each mode returns, and it does so for every kind. Combined with the entitlement note and the sibling exclusion, an agent has everything needed to route and invoke 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. The description earns above that by explaining cross-parameter coupling the schema only gestures at: which `kind` each of game_id and player_id belongs to, that `stat` narrows player history or selects the records stat, and that NFL game output additionally counts line moves. It does not clarify `season` or `games` behavior beyond what the schema states.

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 states a specific verb and resource set: historical opening/closing line movement for games, players, season-long records against the close, and the market report, with the exact return contents enumerated per `kind`. It also names the sibling it is not for (props_research) and the concrete user questions it answers, so an agent can identify it 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?

It opens with explicit when-to-use triggers ("how a game's spread, total or moneyline opened and closed", "which players beat or missed their closing lines") and closes with an explicit exclusion plus the alternative: "Not for tonight's lines and hit rates: use props_research." The `kind` selection logic is also spelled out, leaving nothing to inference.

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