Skip to main content
Glama

Player Props Screener (Pro)

prop_screener
Read-onlyIdempotent

Use this when the user wants the day's player props filtered or ranked across games and stats in one call: who cleared today's line most often over his last 5 or 10 games or the season, whose last-ten median sits furthest from it, where the model's chance differs most from the market's, or the most widely offered lines. Returns the matching rows (player, team, opponent, stat, consensus line and book count, hit rates l5, l10, NBA l20 and season as shares of his games, l10_median and median_diff, model_over, market_over and edge), sorted by sort, with how many matched; players ruled out are left out. With side "under" every rate, gap and edge reads for the under. Requires Keel Stats Pro; the answer says so when the account has none. Not for one player's full props: 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": "prop_screener"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateNoOptional NBA game day (YYYY-MM-DD). Default: today, or the next day with props. The NFL reads the week ahead.
sideNoWhich side the rates, gaps and edges read for (default "over").
sortNoOrder, highest first (default "l10").
statNoOptional stat code or comma-separated codes (NBA: "pts", "reb", "ast", "tpm", "pra", "pr", "pa", "ra", "blk", "stl", "stocks", first quarter "pts_1q", "reb_1q", "ast_1q", first three minutes "pts_f3m", "reb_f3m", "ast_f3m"; NFL: "passing_yards", "rushing_yards", "receiving_yards", "receptions"…). Default: every stat.
limitNoRows to return (default 25, at most 50).
leagueYesLeague ("nba" or "nfl").
min_l5NoOptional: keep the rows whose last-5 hit rate on the side asked is at least this share (0–1, e.g. 0.7).
game_idNoOptional numeric game ID: one game's props only.
min_l10NoOptional: keep the rows whose last-10 hit rate on the side asked is at least this share (0–1, e.g. 0.7).
min_edgeNoOptional: the model's chance minus the market's on the side asked, at least this (e.g. 0.05). Rows without a model reading drop out.
min_booksNoOptional: books offering the line, at least this many.
min_gamesNoOptional: games behind his rates, at least this many (default 3).
min_seasonNoOptional: keep the rows whose season hit rate on the side asked is at least this share (0–1, e.g. 0.7).
min_median_diffNoOptional: his last-ten median minus the line on the side asked, at least this many units.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / stat / description
      Previous value: -"Optional stat code or comma-separated codes (NBA: \"pts\", \"reb\", \"ast\", \"tpm\", \"pra\", \"pr\", \"pa\", \"ra\", \"stocks\"; NFL: \"passing_yards\", \"rushing_yards\", \"receiving_yards\", \"receptions\"…). Default: every stat."New value: +"Optional stat code or comma-separated codes (NBA: \"pts\", \"reb\", \"ast\", \"tpm\", \"pra\", \"pr\", \"pa\", \"ra\", \"blk\", \"stl\", \"stocks\", first quarter \"pts_1q\", \"reb_1q\", \"ast_1q\", first three minutes \"pts_f3m\", \"reb_f3m\", \"ast_f3m\"; NFL: \"passing_yards\", \"rushing_yards\", \"receiving_yards\", \"receptions\"…). Default: every stat."
  2. Added

TDQS

A4.7/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), yet the description adds real behavior: a Keel Stats Pro entitlement is required and the answer reports its absence, players ruled out are omitted, min_edge silently drops rows lacking a model reading, and results are sorted by `sort`. It stops short of describing pagination or truncation behavior beyond the limit field.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the use case, then the returns, then the caveats, all in a compact block with no filler sentences. The dense parenthetical listing the return columns is information-carrying rather than padding.

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?

For a 14-parameter read-only screener with no output schema, the description covers purpose, gating, output shape, sort behavior, and row-exclusion rules. An agent has everything needed to select and call it 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 schema handles field-level documentation, but the description adds semantic glue the schema can't: `side` flips the meaning of every rate, gap and edge, and the returned columns (l5/l10/l20/season as shares, l10_median, median_diff, edge) are explained as the concept each metric expresses. This meaningfully exceeds baseline-3.

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+resource (screen/rank the day's player props across games and stats) and distinguishes itself from the sibling props_research for single-player lookups. The enumerated use cases (who cleared the line, whose median sits furthest from it, biggest model-vs-market divergence, most offered lines) make the tool's identity unmistakable.

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 trigger ('Use this when the user wants the day's player props filtered or ranked...') and closes with an explicit exclusion plus the alternative to use instead ('Not for one player's full props: use props_research'). When-to-use and when-not-to-use are both present.

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