Skip to main content
Glama
Fetchproof MCP Server

Fetchproof MCP Server

races_search

Search finished races by name on a timing platform, optionally filtered by year, to get event or race IDs for results and event lookups.

Instructions

races: Find a race. GET /v1/races/search. Searches finished races by name on one timing platform. Each hit carries the ids /v1/races/events and /v1/races/results take: athlinks hits list their recent editions (event_id), runsignup hits give a race_id, raceroster hits give a numeric event_id. An empty list costs 0 credits. Costs 1 credit when it succeeds. Costs 0 credits when events is empty. Errors, blocked or timed-out requests, invalid requests and cache hits cost nothing. A not-found or empty result is charged only where that operation's published cost says so.

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": {
      "platform": "<platform>",
      "query": "<query>"
    },
    "name": "races_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
yearNoOnly races held in this four-digit year.
queryYesRace name to search for.
platformYesTiming platform: runsignup, athlinks (also carries ChronoTrack events) or raceroster.
cache_max_ageNoServe a cached response when it is newer than this. A cache hit costs 0 credits.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations at all, the description carries the full burden and does meaningful work: it discloses the credit model (1 credit on success, 0 on empty/failed/blocked/timeout/invalid/cache hit) and the per-platform shape of returned ids. It omits auth requirements, rate limits, and pagination/result-count limits, and the final sentence about not-found charging partially muddies the earlier absolute claim that an empty list costs 0 credits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening is well front-loaded and dense with useful routing information, but the cost sentences are redundant: 'An empty list costs 0 credits' and 'Costs 0 credits when events is empty' say the same thing, and the closing sentence about not-found charging restates the exception a third time while introducing ambiguity. Roughly a third of the text is repetitive billing boilerplate.

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 takes on the job of describing what a hit contains per platform, which it does at exactly the level an agent needs to chain into races_events / races_results. The gaps are secondary for this complexity level: no note on result limits, no auth note, and the contradictory-looking charging tail leaves a small unresolved question about billing on empty results.

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 coverage is 100%, so query, platform, year, and cache_max_age are already documented in the schema, and the description repeats the platform list and free-cache behavior rather than extending them. The only genuine addition is what each platform's hits carry downstream (event_id vs race_id vs numeric event_id), which is return-value semantics rather than parameter semantics. Baseline 3 applies.

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 ('Searches finished races by name on one timing platform') and pins down scope with the underlying route GET /v1/races/search. It also distinguishes itself from siblings by explaining that hits carry the ids that races_events and races_results consume, so an agent can tell which tool produces ids and which consumes them.

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 makes the selection condition clear (finished races, searched by name, restricted to one platform at a time) and implicitly routes the agent to races_events / races_results via the returned ids. There is no explicit 'do not use this for X' exclusion and no guidance on choosing among the three platforms beyond a parenthetical about ChronoTrack.

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

Deploy Server

Other Tools