Skip to main content
Glama

The Odds Gap

Ask a Betting Price Question

ask
Read-onlyIdempotent

Ask one whole sports betting price question in plain English, the way a person would: which book pays the most for a bet, hedge math on a ticket, a parlay price, a game's board, a past result or how a line has moved. Returns a plain-sentence answer, the time the prices were scanned and a link to the matching page on theoddsgap.com. When a question could mean more than one game, it returns the choices as plain text to ask again with. A percent above fair in an answer is how far a price sits above our fair price, not expected profit; a middle's figure is how far above or below break-even. Prices may have moved since the scan. Information only: it places no bets and gives no picks.

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": {
      "question": "<question>"
    },
    "name": "ask"
  }
}

Input Schema

NameRequiredDescriptionDefault
questionYesOne whole question, for example 'where is the best price on the Lions moneyline' or 'hedge my Ravens ticket at +240 for $50'.

Output Schema

NameRequiredDescriptionDefault
okYesTrue when the tool produced an answer.
cardNoThe same answer, structured, when there is one. A figure in it keeps its field name (edge_pct, ev_pct) and carries a plain label beside it: "label": "Above Fair" (percent above our fair price, not expected profit) or "Above Break-Even" for a middle.
pageYesThe matching page on theoddsgap.com.
toolNo
as_ofNoWhen the prices were scanned, Eastern Time.
staleNoTrue when that scan is older than usual for our hourly snapshot.
answerYesThe answer in plain sentences.
optionsNoWhen the question could mean more than one thing: whole questions to ask again with.
warningsNo
state_noteNoWhere to check what is legal for you.
decline_kindNoSet when the question is one we do not answer, and which kind.
free_left_todayNo
responsible_gamblingYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / properties / card / description
      Previous value: -"The same answer, structured, when there is one."New value: +"The same answer, structured, when there is one. A figure in it keeps its field name (edge_pct, ev_pct) and carries a plain label beside it: \"label\": \"Above Fair\" (percent above our fair price, not expected profit) or \"Above Break-Even\" for a middle."
  2. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, yet the description adds substantial context beyond them: the exact answer payload (plain-sentence answer, scan timestamp, link), the ambiguity re-ask loop, and the meaning of "percent above fair" versus a middle's break-even figure. It also warns that prices may have moved since the scan and states it places no bets and gives no picks.

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 a single front-loaded paragraph: purpose first, then return shape, then the disambiguation rule, then interpretive caveats. Every sentence carries information, though the fair-price and middle definitions are dense enough that they could be split for faster scanning.

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?

Although an output schema exists and return values technically need not be described, the description covers the one thing a schema cannot: what ambiguous input causes and what the agent should do next. Combined with the fair-price interpretation note and staleness warning, nothing an agent needs to call this correctly 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?

With a single fully documented parameter the schema baseline is already a 3, and the description adds meaning by insisting on "one whole question" phrased the way a person would speak, which explains the single-string design and the 400-character limit. The concrete phrasing examples themselves live in the schema, not the description.

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?

"Ask one whole sports betting price question in plain English" gives a specific verb and resource, and the enumeration of supported topics (best price, hedge math, parlay price, board, past result, line movement) makes the scope concrete. It does not name any sibling (calc, middles, game_lines, past_game) to draw the boundary, so an agent must infer when the structured alternatives are preferable.

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?

The list of question categories plus the ambiguity clause ("returns the choices as plain text to ask again with") tells the agent what kinds of input belong here and what to expect from a vague one. There is no exclusion or explicit routing to the structured siblings for the same information, so it stops short of full when/when-not guidance.

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