Skip to main content
Glama

Market odds

get_market_odds
Read-onlyIdempotent

Use for the extra betting markets of a game as history: the regulation result (three-way, a draw is possible), the 1st period result and puck line, and the 1st, 2nd and 3rd period totals. Pass game_id (from get_schedule or get_games) and market. For each sportsbook it returns the opening line (the first one we captured) and the closing line (the last one before the game started), each as the list of outcomes with their point and American price, plus captured_at and minutes_before_start (negative when the last capture came after our scheduled start, which the sportsbooks' listed start can run past). Most books were captured once, so opening and closing are often the same line. Held from May 2023 (the 2022-23 playoffs) for the larger sportsbooks only; not every game has every market. Each game's lines are added the morning after it is played. Costs 10 credits a call; a game with no lines is refunded. Set estimate_only to get the price without being charged. For the full-game moneyline, spread and total use get_odds. 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": {
      "game_id": "<game_id>",
      "market": "<market>"
    },
    "name": "get_market_odds"
  }
}

Input Schema

NameRequiredDescriptionDefault
marketYesThe market: h2h_3_way (regulation result: home, draw or away after 60 minutes), totals_p1 (1st period total goals), totals_p2 (2nd period total goals), totals_p3 (3rd period total goals), h2h_p1 (1st period result: home, draw or away), spreads_p1 (1st period puck line)
game_idYesGame id from get_schedule or get_games.
bookmakerNoOne bookmaker key, e.g. draftkings, fanduel, pinnacle.
estimate_onlyNoReturn what this call would cost, without charging or running it.

Output Schema

NameRequiredDescriptionDefault
noteNo
toolNo
booksYes
countYes
labelYes
marketYes
creditsNo
game_idYes
estimate_onlyNo
scheduled_startYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior3/5

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

The description goes well beyond the readOnly/idempotent annotations: it discloses a 10-credit cost with refund on empty results, the estimate_only bypass, historical coverage starting May 2023 for larger books only, the post-game ingestion lag, and the meaning of negative minutes_before_start. That is substantial added context, but the billing behavior (charging credits on a readOnly-annotated tool) is asserted without reconciling it against the 'no side effects' framing, which is the one place an agent could be surprised.

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?

Purpose and cost model are front-loaded and every sentence carries information (definition of opening/closing, capture timing, coverage window, sibling redirect). It is dense to the point of long parenthetical clauses, particularly the closing-line and minutes_before_start sentence, which could be split for faster parsing.

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?

Even though an output schema exists, the description explains the shape of the returned lines (per-book opening/closing, outcomes with point and American price, captured_at, minutes_before_start) so an agent can interpret the payload. Combined with prerequisites, cost, historical window, and the explicit 'no tool places, accepts or tracks wagers' disclaimer, nothing material is 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 100%, so the baseline is 3, and the market enum is already fully glossed in the schema. The description still adds domain context — that a draw is possible in the three-way market and that puck line means spreads_p1 — and ties estimate_only to the credit mechanism, which the schema states but does not connect to the surrounding cost rules. bookmaker is never mentioned in the description but is self-explanatory in 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 opens with a specific statement of what is returned — historical odds for the extra markets (regulation three-way, 1st period result and puck line, period totals) — and explicitly carves out the sibling it is not: 'For the full-game moneyline, spread and total use get_odds.' An agent can route between the two without opening either schema.

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?

It gives the triggering condition (extra/period markets), the prerequisite source for game_id (get_schedule or get_games), the alternative for standard markets (get_odds), and the escape hatch for cost checking (estimate_only). It also sets expectations about when data is absent, so an agent knows not to retry on an empty result.

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.