Skip to main content
Glama

Browse the event board

find_matches
Read-onlyIdempotent

Returns the in-play or not-yet-started fixtures of a single sport, one short row per match, each with its full-game moneyline attached. This is where event_id values for match_prices come from. To shrink the board, give query a few whitespace-separated terms; a match is kept only when every term occurs in its league, home or away name, ignoring case (for instance 'serie a juventus'). At most limit rows come back and a closing note states how many were left out. Each call is billed as one request on the key's plan, so hold on to ids you have already fetched instead of listing the board again.

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": "find_matches"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNo'live' for matches in progress, 'prematch' for fixtures that have not startedlive
limitNoMaximum number of rows to return
queryNoSearch terms; a match is returned only if every term is found in its league, home or away name
sportYesNumeric sport id from board_sports, or a name/alias such as 3, 'tennis' or 'NHL'
response_formatNo'detailed' also returns the main handicap and total line, plus has_oddsconcise

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only declare readOnly/idempotent/openWorld; the description adds materially more: per-call billing against the key's plan, a truncation signal ('a closing note states how many were left out'), and the provenance role of event_id. These are behaviors an agent cannot recover from the annotations or schema.

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?

Four sentences, front-loaded with the purpose, then filtering, then truncation, then cost guidance. Every sentence carries information, though the billing sentence is slightly long-winded and could be tightened without loss.

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 carries the return-value burden and does so adequately: row shape, moneyline presence, and truncation reporting. It defers the richer 'detailed' fields to the schema's response_format description, which is reasonable, though an agent gets no sense of row size or ordering.

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 already 100%, so the baseline is 3. The description still adds value by spelling out the AND-across-terms semantics, the case-insensitivity, the fields searched, and a worked example ('serie a juventus'), plus how `limit` manifests as a leftover-count note. `mode` and `response_format` are left entirely to 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?

States a specific verb and resource with scope: in-play or not-yet-started fixtures of a single sport, one row per match with the full-game moneyline. It also positions itself in the ecosystem by naming match_prices as the consumer of the event_id values it returns, which separates it from siblings like board_sports and price_moves.

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 concrete when-to-use guidance for `query` (whitespace-separated terms, all must match) and an explicit anti-pattern: do not re-list the board, hold on to ids because each call is billed. It does not state when a sibling such as upcoming_lines or price_moves is the better choice, so it stops short of full alternative routing.

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