Skip to main content
Glama

Player Props Research, Model & Cheat Sheet

props_research
Read-onlyIdempotent

Use this when the user asks about a player's prop lines, how often he clears a line, or today's prop board. Returns, for a player_id, one compact row per stat with a line for his next game: the consensus line and book count, his last five games against it (l5, values newest first) and his season average; signed in, the last ten (l10, newest first) and his record against the closing line; with Keel Stats Pro also L20 and season hit rates, the opening line and move, the model's probability against the market's, the best price at the consensus line (best_over/best_under name their line; a better line at another book follows as other_line), the matchup and (NBA) open_looks, his shooting by defender distance beside what his next opponent allows at each distance, and (NBA points, rebounds, assists) his last games' result, closing line and tracking rates (opportunity_games, a few without Pro), and with detail the book-by-book odds, closing lines, game log, history and alternate ladders. Without a player_id, today's prop board: recent is the last five values newest first, status the injury report's (questionable, doubtful…), minutes_l5 and fga_l5/tpa_l5 the last five games' minutes and attempts; players ruled out are listed in ruled_out, not in the rows (Pro: model edge, the daily cheat sheet and the consistent filter). The answer's account.held names what the caller's plan left out. Not for picks: it is research only and never gives a pick.

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": "props_research"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateNoOptional date (YYYY-MM-DD) for the NBA daily prop board.
statNoOptional stat code: narrows a player's rows and sections, or picks the board's stat (e.g. NBA: "pts", "reb", "ast", "tpm", "pra"; NFL: "passing_yards", "rushing_yards", "receiving_yards", "receptions").
detailNoWith a player_id (Keel Stats Pro): "compact" (default), "full" (every section, the long answer), or a comma-separated list of sections: "books" (book-by-book odds and history), "ladders" (alternate lines graded), "closes" (closing lines per game), "games" (the game log with closes), "history" (record against the close by season).
leagueYesLeague ("nba" or "nfl").
game_idNoOptional numeric game ID to filter the daily prop board to a single game.
player_idNoOptional numeric player ID to inspect his lines for the next game. Omit for the daily prop board.
consistentNoOptional, the board only (Keel Stats Pro): true keeps the players whose last 5 and last 10 games both went one way against today's line (70%+ over, or 70%+ under), read over the whole board before it is cut to its rows.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / consistent
      Added value: +{
      +  "description": "Optional, the board only (Keel Stats Pro): true keeps the players whose last 5 and last 10 games both went one way against today's line (70%+ over, or 70%+ under), read over the whole board before it is cut to its rows.",
      +  "type": "boolean"
      +}
  2. Changed3 schema fields changed
    • addedInput schema / properties / detail
      Added value: +{
      +  "description": "With a player_id (Keel Stats Pro): \"compact\" (default), \"full\" (every section, the long answer), or a comma-separated list of sections: \"books\" (book-by-book odds and history), \"ladders\" (alternate lines graded), \"closes\" (closing lines per game), \"games\" (the game log with closes), \"history\" (record against the close by season).",
      +  "type": "string"
      +}
    • changedInput schema / properties / player_id / description
      Previous value: -"Optional numeric player ID to inspect his upcoming lines, book-by-book odds, line comparisons, closing-line record, and ladders. Omit for the daily prop board and cheat sheet."New value: +"Optional numeric player ID to inspect his lines for the next game. Omit for the daily prop board."
    • changedInput schema / properties / stat / description
      Previous value: -"Optional stat code for the daily board or book-by-book view (e.g. NBA: \"pts\", \"reb\", \"ast\", \"tpm\", \"pra\"; NFL: \"passing_yards\", \"rushing_yards\", \"receiving_yards\", \"receptions\")."New value: +"Optional stat code: narrows a player's rows and sections, or picks the board's stat (e.g. NBA: \"pts\", \"reb\", \"ast\", \"tpm\", \"pra\"; NFL: \"passing_yards\", \"rushing_yards\", \"receiving_yards\", \"receptions\")."
  3. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Annotations only declare a safe read; the description adds substantial behavior the agent could not otherwise know: results are tiered by subscription ('signed in', 'with Keel Stats Pro'), `account.held` reports what the caller's plan omitted, ruled-out players are moved out of rows into `ruled_out`, and some tracking fields are 'a few without Pro'. That is real disclosure of entitlement-gated and filtered behavior beyond the annotations.

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 first sentence is well front-loaded and the closing caveat is well placed, but the middle is one enormous run-on clause chain enumerating output fields that is hard to parse on first read. It is not padded with filler, yet it would be far easier to scan if split into player-mode and board-mode paragraphs.

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 and a complex, two-mode tool, the description carries the return-value burden and does it thoroughly: field-by-field semantics for l5/l10, best_over/best_under and other_line, recent/status/minutes_l5, ruled_out, and what `detail` unlocks. An agent has enough to call it and interpret the response correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents all seven parameters, including `detail` section names and the `consistent` filter. The description mostly restates those (omitting player_id yields the board) rather than adding syntax or constraints the schema lacks, so the baseline of 3 applies.

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?

Opens with a concrete trigger ('when the user asks about a player's prop lines, how often he clears a line, or today's prop board') and then states the exact resource shape: one compact row per stat with consensus line, l5, season average. The player-mode vs board-mode split is explicit, so an agent can distinguish this from prop_screener or line_shop without opening a 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?

Gives clear triggering conditions and an explicit negative case ('Not for picks: it is research only and never gives a pick'), which prevents misuse. It also encodes mode selection through player_id presence. It stops short of naming which sibling to use instead for picks, screening, or line shopping, so routing to alternatives is left 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