Skip to main content
Glama

DunkAPI

Prop history

get_prop_history
Read-onlyIdempotent

Use to see how a player did against his prop line over time: for one market (points, rebounds, assists, threes, blocks, steals, one of the combos (points + rebounds + assists, points + rebounds, points + assists, rebounds + assists), double-double or triple-double), one row per game with the closing line (the median across books, or one book's), the opening line (the same as the close wherever only one capture was taken), the prices, what the player actually recorded from our box scores and the result against the line, plus the over rate, up to 200 games a call. Costs 10 credits for every 25 games already played that a call covers, and at least 10 a call (accounts opened before November 1 2026 pay 10 a call). Set estimate_only to get the price without being charged. Prices are market information; no tool places, accepts or tracks wagers.

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": {
      "player_id": "<player_id>",
      "market": "<market>"
    },
    "name": "get_prop_history"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoGames to return, oldest first (default 50, max 200). next_from_date says where to continue.
leagueNoLeague. Defaults to nba. One of: nba, wnba, ncaam.
marketYesThe market: player_points (points), player_rebounds (rebounds), player_assists (assists), player_threes (three-pointers made), player_points_rebounds_assists (points + rebounds + assists), player_blocks (blocks), player_steals (steals), player_points_rebounds (points + rebounds), player_points_assists (points + assists), player_rebounds_assists (rebounds + assists), player_double_double (double-double (over = yes)), player_triple_double (triple-double (over = yes))
to_dateNoLast date, YYYY-MM-DD (the game's date).
bookmakerNoOne book's closing line instead of the median across books, e.g. draftkings.
from_dateNoFirst date, YYYY-MM-DD (the game's date).
player_idYesPlayer id (e.g. 3945274) from search_players.
estimate_onlyNoReturn what this call would cost, without charging or running it.

Output Schema

NameRequiredDescriptionDefault
noteNo
statYes
toolNo
countYes
gamesYes
marketYes
creditsNo
summaryYes
bookmakerYes
player_idYes
truncatedNo
player_nameYes
estimate_onlyNo
next_from_dateNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / market / description
      Previous value: -"The market: player_points (points), player_rebounds (rebounds), player_assists (assists), player_threes (three-pointers made), player_points_rebounds_assists (points + rebounds + assists), player_blocks (blocks), player_steals (steals)"New value: +"The market: player_points (points), player_rebounds (rebounds), player_assists (assists), player_threes (three-pointers made), player_points_rebounds_assists (points + rebounds + assists), player_blocks (blocks), player_steals (steals), player_points_rebounds (points + rebounds), player_points_assists (points + assists), player_rebounds_assists (rebounds + assists), player_double_double (double-double (over = yes)), player_triple_double (triple-double (over = yes))"
    • changedInput schema / properties / market / enum
      Previous value: -[
      -  "player_points",
      -  "player_rebounds",
      -  "player_assists",
      -  "player_threes",
      -  "player_points_rebounds_assists",
      -  "player_blocks",
      -  "player_steals"
      -]New value: +[
      +  "player_points",
      +  "player_rebounds",
      +  "player_assists",
      +  "player_threes",
      +  "player_points_rebounds_assists",
      +  "player_blocks",
      +  "player_steals",
      +  "player_points_rebounds",
      +  "player_points_assists",
      +  "player_rebounds_assists",
      +  "player_double_double",
      +  "player_triple_double"
      +]
  2. Changed1 schema field changed
    • addedInput schema / properties / estimate_only
      Added value: +{
      +  "description": "Return what this call would cost, without charging or running it.",
      +  "type": "boolean"
      +}
  3. First observed

TDQS

A3.9/5.0
Behavior5/5

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

Beyond the read-only/idempotent annotations, the description discloses the cost model (10 credits per 25 games played, minimum 10, with a grandfather clause), a hard cap of 200 games per call, and that estimate_only returns the price without charging or running the query. It also states the data-handling caveat that the opening line equals the close where only one capture exists, and clarifies the tool only reports prices and never 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.

Conciseness3/5

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

The purpose is front-loaded in the opening clause, which is good, but the middle devolves into a long run-on clause that re-lists every market already fully documented in the schema enum, spending words without adding information. The cost and estimate_only sentences earn their place; the market recital does not.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

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 values, yet it still characterizes the row shape usefully. For an 8-parameter, credit-metered tool it covers cost, cap, and bookmaker behavior; the only thin spot is that continuation via next_from_date is left to the schema rather than reinforced in the description.

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 real meaning: it explains that the closing line defaults to the median across books unless one book's line is requested, which clarifies the bookmaker parameter's effect. It also ties the 200-game limit to the limit parameter and frames estimate_only as a dry-run flag.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a concrete verb and resource: see how a player performed against a prop line over time, one row per game, for a named market. It enumerates exactly what each row contains (closing line, opening line, prices, actual box-score result, over rate), so an agent knows precisely what comes back. It stops short of naming which sibling to use instead (e.g. get_prop_movement, get_prop_backtest, get_player_props), leaving sibling differentiation to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

"Use to see how a player did against his prop line over time" gives an implied when-to-use frame, and the estimate_only note tells the agent how to price a call cheaply. However there is no explicit when-not guidance and no named alternative for related questions like line movement or backtesting, so routing still depends on the agent inferring from sibling names.

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.