Skip to main content
Glama

Player props

get_player_props
Read-onlyIdempotent

Use for player prop lines by sportsbook: the anytime goalscorer price (Yes in over_odds, No in under_odds where posted, no line) and, for the top five leagues, MLS and the Champions League, first and last goalscorer, to be carded, shots on target, shots and assists over/unders (most books post only the over), from DraftKings, FanDuel, William Hill and Pinnacle as the archive holds them. Pass game_id for every player's props in one game, or player_id with from_date (and to_date) for one player across games (up to 100). A game costs 10 credits before it starts and 20 once it has (accounts opened before October 30 2026 pay 10 for every game). Returns the closing line by default (the last before the game starts) or the opening line, with each book's over and under prices. Each row has captured_at, scheduled_start and minutes_before_scheduled_start (negative when captured after the scheduled start); a row is kept when it was captured before the sportsbooks' listed start, which in the NBA is usually about 10 minutes after the scheduled one, so filter on minutes_before_scheduled_start > 0 for a strictly before-schedule backtest. Outside football the archive mostly holds one pre-game capture per line, so the opening and closing lines are usually the same; the opening line differs only where a second capture was taken (live capture from October 2026, and wherever else it is held). Set estimate_only to get the price without being charged. Prices are market information; no tool places, accepts or tracks wagers.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_player_props"
  }
}

Input Schema

NameRequiredDescriptionDefault
leagueNoLeague. Defaults to soccer. One of: soccer, mls, laliga, seriea, bundesliga, ligue1, ucl.
marketNoOne market: player_goal_scorer_anytime (anytime goalscorer (over = scores)), player_shots_on_target (shots on target), player_shots (shots), player_assists (assists), player_first_goal_scorer (first goalscorer (over = scores the match's first goal)), player_last_goal_scorer (last goalscorer (over = scores the match's last goal)), player_to_receive_card (to be carded (over = shown a yellow or red card))
game_idNoGame id: every player's props for that game.
to_dateNoWith player_id: last date (default: no end), YYYY-MM-DD (the game's date).
bookmakerNoBookmaker key, e.g. draftkings, fanduel, pinnacle.
from_dateNoWith player_id: first date, YYYY-MM-DD (the game's date).
player_idNoPlayer id (e.g. 280555) from search_players. With from_date: that player's props across games.
estimate_onlyNoReturn what this call would cost, without charging or running it.
snapshot_typeNoclosing (default): the last line before the game starts. opening: the first one captured, which is the same capture as the close wherever only one was taken.

Output Schema

NameRequiredDescriptionDefault
noteNo
toolNo
countNo
gamesNo
propsNo
creditsNo
estimate_onlyNo
snapshot_typeNo
next_from_dateNo
credits_per_gameNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / market / description
      Previous value: -"One market: player_goal_scorer_anytime (anytime goalscorer (over = scores)), player_shots_on_target (shots on target), player_shots (shots), player_assists (assists)"New value: +"One market: player_goal_scorer_anytime (anytime goalscorer (over = scores)), player_shots_on_target (shots on target), player_shots (shots), player_assists (assists), player_first_goal_scorer (first goalscorer (over = scores the match's first goal)), player_last_goal_scorer (last goalscorer (over = scores the match's last goal)), player_to_receive_card (to be carded (over = shown a yellow or red card))"
    • changedInput schema / properties / market / enum
      Previous value: -[
      -  "player_goal_scorer_anytime",
      -  "player_shots_on_target",
      -  "player_shots",
      -  "player_assists"
      -]New value: +[
      +  "player_goal_scorer_anytime",
      +  "player_shots_on_target",
      +  "player_shots",
      +  "player_assists",
      +  "player_first_goal_scorer",
      +  "player_last_goal_scorer",
      +  "player_to_receive_card"
      +]
  2. Changed2 schema fields changed
    • changedInput schema / properties / market / description
      Previous value: -"One market: player_goal_scorer_anytime (anytime goalscorer (over = scores))"New value: +"One market: player_goal_scorer_anytime (anytime goalscorer (over = scores)), player_shots_on_target (shots on target), player_shots (shots), player_assists (assists)"
    • changedInput schema / properties / market / enum
      Previous value: -[
      -  "player_goal_scorer_anytime"
      -]New value: +[
      +  "player_goal_scorer_anytime",
      +  "player_shots_on_target",
      +  "player_shots",
      +  "player_assists"
      +]
  3. Changed2 schema fields changed
    • addedOutput schema / properties / props / items / properties / minutes_before_scheduled_start
      Added value: +{
      +  "type": [
      +    "number",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / props / items / properties / scheduled_start
      Added value: +{
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
  4. Changed1 schema field changed
    • changedInput schema / properties / snapshot_type / description
      Previous value: -"closing (default): the last line before the game starts. opening: the first one captured."New value: +"closing (default): the last line before the game starts. opening: the first one captured, which is the same capture as the close wherever only one was taken."
  5. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial context beyond them: credit pricing (10 pre-game, 20 after, legacy 10), estimate_only to avoid charges, the capture-time retention rule, the NBA ~10-minute discrepancy caveat with a concrete filter (minutes_before_scheduled_start > 0), and the typical single-capture behavior outside football. It also explicitly states no tool places or tracks wagers.

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 purpose and access patterns, and nearly every sentence carries operational information. It is a single dense paragraph, though, and the market enumeration plus billing caveats make it long enough that a reader must re-read the middle clauses; some compression into bullet-like ordering would help.

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 an output schema present, the description does not need to document return fields, yet it still covers the two snapshot modes, per-book over/under prices, and the row timestamps that matter for backtesting. Given 9 optional parameters, cost model, and archive quirks, the definition is complete enough to call correctly.

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

Parameters5/5

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

Schema coverage is 100%, so 3 is the baseline, but the description adds genuine meaning: it explains per-market odds semantics (Yes in over_odds, No in under_odds where posted, no line), that most books post only the over, the game_id-vs-player_id pairing rules, and the up-to-100 result cap. That is meaning an agent cannot get from the schema alone.

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 specific verb and resource ('player prop lines by sportsbook') and enumerates exactly what is covered: anytime goalscorer pricing conventions, plus first/last goalscorer, to be carded, shots on target, shots and assists for the top five leagues, MLS and UCL. It also names the four source books, so an agent can distinguish this from a general odds tool 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 explicit access patterns: 'Pass game_id for every player's props in one game, or player_id with from_date (and to_date) for one player across games (up to 100)', which resolves the main query-shape decision. It also states when to prefer opening vs closing and when to use estimate_only. It stops short of naming sibling tools such as get_prop_history or get_prop_movement as alternatives.

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.