infersports

Find Arbitrage

find_arbitrage

Read-only

Find cross-book arbitrage in a fixture — a guaranteed-profit price split — in ONE call.

Resolves the fixture, then for each market/line takes the best price per outcome across books;
when the inverse prices sum to < 1 there is a locked margin regardless of result. Reports the
margin % and which book holds each leg (legs must come from ≥2 distinct books). DETECTION ONLY:
no stake sizing, no bet links — InferSports is read-only.

Args:
    query: natural-language fixture, e.g. "Netherlands vs Algeria" or a single team.
    markets: optional filter — any of "1x2", "asian_handicap", "totals" (default: all).
    period: optional — "full_time" or "half_time" (default: both).
    min_margin_pct: only report opportunities with at least this guaranteed margin (default 0).
    format: odds format — decimal | hk | malay | american | indonesian | probability.
    sport: optional filter — "football" or "basketball".
    date: optional UTC date "YYYY-MM-DD" to disambiguate same-name fixtures.

On an ambiguous query, ``status`` is "ambiguous" and ``ask_user`` carries a prompt — do not guess.

Input Schema

TableJSON Schema

Name	Required	Default
`date`	No
`query`	Yes
`sport`	No
`format`	No	decimal
`period`	No
`markets`	No
`min_margin_pct`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedJun 7, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Beyond the readOnlyHint annotation, the description adds rich behavioral context: it explains the arbitrage detection algorithm (inverse prices sum < 1), the requirement of ≥2 distinct books, that it reports margin % and leg-owning books, and the ambiguous-query behavior with 'status' and 'ask_user'. This goes well beyond annotation coverage.

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 description is longer than minimal but every sentence earns its place: definition, algorithm, detection disclaimer, and parameter list. It is front-loaded with the core purpose and the parameter list is logically ordered. Slight redundancy in mentioning read-only twice could be trimmed, but it remains efficient.

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 tool with 7 parameters, no output schema, and a nontrivial algorithm, the description covers the essential invocation details and expected output (margin % and book per leg). It also handles the ambiguous-query edge case. It does not enumerate all possible statuses or error responses, but that is a minor gap given the complexity; a 4 reflects solid completeness without being exhaustive.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With schema description coverage at 0%, the description fully compensates by explaining every parameter: query with example, markets with allowed values, period values, min_margin_pct semantics, format options, sport filter, and date for disambiguation. No parameter is left unexplained, so an agent can compose arguments correctly without schema hints.

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 verb and resource: 'Find cross-book arbitrage in a fixture — a guaranteed-profit price split — in ONE call.' It clearly distinguishes from sibling tools like find_value (value betting) and compare_lines (line comparison) by stating the single-call resolution and detection-only scope, making the tool's identity unmistakable.

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 explicitly states when-not: 'DETECTION ONLY: no stake sizing, no bet links — InferSports is read-only,' and instructs not to guess on ambiguous queries. However, it does not name specific alternative tools (e.g., find_value for stake sizing) or provide a condition for choosing this over a sibling, so it stops short of a full 5.

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

All infersports 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.

Resources

Need Help?