Skip to main content
Glama

Best price across books

invoke_best_price
Read-onlyIdempotent

Added after you connected: the first call asks you to approve it. Line shopping: the best price for a bet across DraftKings, FanDuel, BetMGM, Caesars, Kalshi and Polymarket US, with every book's price, the no-vig fair price (from books that post both sides) and the EV of the best price. Works for moneyline, spread, total and player props in the NBA, NFL and NHL, UFC moneylines, and PGA golf outrights (sport pga, market prop, stat win, top5, top10, top20 or make_cut; FanDuel and Kalshi, shown before Thursday lock). Golf winner odds carry about 50% vig, so no EV is shown when the vig on a market is above 25%. Filter by team, player, market, stat and line. Rows sort by EV. Each price has a bet_url that opens that book (the bet slip where the book supports it). For our model edge on a prop, call the sport's props tool too.

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": {
      "sport": "<sport>"
    },
    "name": "invoke_best_price"
  }
}

Input Schema

NameRequiredDescriptionDefault
lineNoOnly this line, for example 24.5 or 3.5.
statNoProp stat: points, rebounds, assists, three_pm, pra, steals, blocks, pass_yds, rush_yds, rec_yds, rec, pass_td, goals, shots, saves. Golf: win, top5, top10, top20, make_cut.
teamNoTeam abbreviation, for example DET. Returns that team's games and players.
limitNoRows, default 20, most 60.
sportYesSport. mma is UFC. pga is golf outrights.
marketNoml is moneyline.
playerNoPlayer or fighter name, for example Cade Cunningham.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description still adds genuine context beyond that: the first-call approval prompt after connecting, the vig-based suppression of EV output, the sorting of rows by EV, and that each price carries a bet_url. No return-format or pagination detail beyond that, so it is solid but not exhaustive.

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?

It is dense but nearly every sentence carries actionable information, and the core purpose is stated immediately after the approval note. There is some redundancy with the schema (re-listing golf stat values and the filter fields), which prevents a 5.

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 no output schema, the description does explain the returned columns (per-book price, no-vig fair price, EV, bet_url) and default row sorting, which is the important part. It omits pagination behavior and full response shape, but the definition covers enough for correct invocation of this 7-parameter tool.

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?

Schema description coverage is 100%, so every parameter including enums is already documented, making 3 the baseline. The description adds only marginal value, notably the golf parameter combination (sport pga with market prop and stat win/top5/top10/top20/make_cut) and the note that mma means UFC, which largely restates schema content.

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?

States a precise verb+resource: finds the best price for a bet across six named sportsbooks, returning each book's price, no-vig fair price and EV. It enumerates the supported sports/markets (NBA, NFL, NHL, UFC moneylines, PGA outrights) and thereby distinguishes itself from single-book odds siblings like invoke_mlb_game_odds.

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 clear context for when to call it (line shopping across books) and explicit constraints such as no EV shown when market vig exceeds 25%, and golf outrights appearing only before Thursday lock. It also routes the agent elsewhere for a related need: 'For our model edge on a prop, call the sport's props tool too.' There is no explicit statement of when NOT to use it, keeping it short of a 5.

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.

Resources