Skip to main content
Glama

Odds

get_odds
Read-onlyIdempotent

Use for betting lines: each sportsbook's three-way moneyline (home, draw, away), goal handicap and total (opening and closing from June 2020 for 16 competitions and from 2024 for the rest; before that most books carry one final pre-match line), the no-margin probabilities each book's prices imply, and for finished matches the result and whether the total went over against the median close. Pass game_id for one match (5 credits), date for a day's matches (10 credits), or season (optionally a team) for a season of priced matches, 2 credits per match returned, up to 100 a page. 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_odds"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateNoA day's matches, YYYY-MM-DD (UTC).
teamNoWith season: one club's matches.
limitNoWith season: matches per page (default 50).
leagueNoLeague. Defaults to soccer. One of: soccer, mls, laliga, seriea, bundesliga, ligue1, ucl, championship, nwsl, ligamx, uel, uecl, eredivisie, primeira, scotland, brazil, argentina.
offsetNoWith season: page offset; use next_offset.
seasonNoA season of priced matches, by the year it starts (2025 = 2025-26; MLS, the NWSL, Liga MX, Brazil and Argentina: the calendar year).
game_idNoOne match.

Output Schema

NameRequiredDescriptionDefault
noteNo
toolNo
countNo
gamesNo
creditsNo
next_offsetNo
estimate_onlyNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description still earns credit for genuinely non-obvious behavior: historical coverage boundaries (June 2020 for 16 competitions, 2024 for the rest, single final pre-match line before that), per-request credit pricing, and the 100-per-page cap. Missing are failure modes (what happens for a match with no priced markets) and whether no-margin probabilities are computed or supplied.

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?

It is front-loaded with the payload contents, which is the right order, and the second sentence handles invocation and cost. However, the first sentence is a single dense enumeration of six data types with parenthetical coverage caveats that is hard to parse on one pass, and the coverage dates arguably belong after the invocation guidance rather than buried mid-sentence.

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?

For a 7-parameter historical data tool with an output schema, this is close to complete: coverage windows, pricing, pagination, and the informational-only nature of the data are all stated. The remaining gap is relational — with siblings like get_market_odds and get_line_movement in the catalog, the agent is not told when this tool is the right one versus those.

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?

With 100% schema description coverage, the baseline is 3, and the schema already documents date format, league enum, season year convention, and next_offset pagination. The description adds real value on top by attaching a credit price to each parameter mode and stating the page cap, but it does not clarify the interplay of season+team+limit+offset beyond what the schema implies.

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 names a specific resource and enumerates its contents precisely: three-way moneyline (home/draw/away), goal handicap, total with opening and closing lines, no-margin implied probabilities, and settled results including over/under against the median close. That is far beyond a name restatement. It stops short of distinguishing itself from the overlapping sibling get_market_odds, so an agent must still open both to know which to call.

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 clearly routes among the three mutually exclusive parameter modes: game_id for one match, date for a day's slate, season (optionally with team) for a season of priced matches, each with its own credit cost. It also closes off a wrong assumption with 'no tool places, accepts or tracks wagers.' What it does not do is name an alternative tool for cases where this one is the wrong choice.

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.