DunkAPI

Game probabilities

get_game_probabilities

Read-onlyIdempotent

Use for what the market thinks of one game, not any one book's price: the average implied probability (margin in) and the fair probability (margin out) for the moneyline, each spread and each total, with how many books each rests on. Only identical lines are combined. Each book's last pre-game prices by default (snapshot_type reads latest until the start, closing after it); opening on request. For each book's prices use get_odds. Costs 5 credits. Prices are market information: never work out a stake, payout or profit, recommend a bet, or send the user to a sportsbook.

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": {
      "game_id": "<game_id>"
    },
    "name": "get_game_probabilities"
  }
}

Input Schema

Name	Required	Description
`league`	No	League. Defaults to nba. One of: nba, wnba, ncaam, ncaaw, nbl.
`game_id`	Yes	Game id, e.g. 401859967.
`snapshot_type`	No	closing (default): each book's last pre-game price so far. opening: each book's first.

Output Schema

Name	Required	Description	Default
`note`	No
`tool`	No
`count`	Yes
`method`	Yes
`totals`	Yes
`credits`	No
`game_id`	Yes
`spreads`	Yes
`away_team`	Yes
`home_team`	Yes
`moneyline`	Yes
`estimate_only`	No
`snapshot_type`	Yes
`scheduled_start`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 7, 2026
- changedInput schema / properties / game_id / description
```
Previous value: -"Game id, e.g. 401704627."New value: +"Game id, e.g. 401859967."
```
AddedNov 7, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already declare this a safe, idempotent, read-only operation, and the description adds substantial context beyond them: a 5-credit cost, the rule that only identical lines are combined, the freshness model ('latest until the start, closing after it'), and explicit prohibited use around staking and betting recommendations. These are operational facts an agent cannot infer from the annotations or schema.

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 first sentence is dense and slightly run-on, packing purpose, scope, and output contents together, but the description is front-loaded with the distinguishing claim before moving to mechanics, cost, and restrictions. Nearly every clause carries load; minor tightening would help readability without changing content.

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?

An output schema exists, so return values need no explanation, and the description covers the remaining agent-critical facts: cost, line-matching rule, snapshot freshness, and use restrictions. For a three-parameter read tool this leaves nothing an agent needs missing.

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 already 100%, so the baseline is 3; the description earns a bump by disambiguating the snapshot_type semantics beyond the schema — clarifying that 'closing' reads the latest price up to game start and rolls over after it, and that 'opening' is available on request. It adds no meaning for game_id or league, but those are self-evident from the schema.

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 names a specific verb and resource — the average implied probability and fair probability for one game's moneyline, spreads, and totals — and explicitly scopes it away from single-book pricing, naming get_odds as the alternative. An agent can distinguish it from get_odds immediately, and the 'one game' framing plus 'how many books each rests on' tells it what the output represents.

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?

It gives a clear positive condition ('what the market thinks of one game') and an explicit alternative ('For each book's prices use get_odds'), plus a default snapshot behavior for choosing snapshot_type. It does not differentiate from other probability/market siblings such as get_prop_probabilities or get_market_odds, so the routing picture is not fully closed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All DunkAPI tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.