Skip to main content
Glama

search_exercises

Read-only

Search the exercise catalog by free-text name (e.g. 'barbell squat'). Returns real catalog exercises with an id, sorted by matchConfidence (0-1, fraction of your query's words found on that catalog entry). Call this for each exercise before create_workout_plan. Use the top result's exact id as that exercise's exerciseId and its name as the exercise name only when its matchConfidence is high (roughly 0.7+) — the app resolves the image/video from exerciseId automatically, so a matched exerciseId is what makes the exercise show media in the app. If every result has low matchConfidence, or there are no results at all, don't guess — fall back to a plain name with no exerciseId rather than linking a wrong exercise's image.

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": {
      "query": "<query>"
    },
    "name": "search_exercises"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
queryYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / limit / default
      Added value: +8
    • removedInput schema / properties / limit / description
      Removed value: -"Matches per name (default 4, or 3 per name with queries)."
    • removedInput schema / properties / queries
      Removed value: -{
      -  "description": "Several exercise names in one call; returns the top matches for each.",
      -  "items": {
      -    "minLength": 1,
      -    "type": "string"
      -  },
      -  "maxItems": 30,
      -  "type": "array"
      -}
    • addedInput schema / required
      Added value: +[
      +  "query"
      +]
  2. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Annotations only declare readOnlyHint and openWorldHint=false; the description adds the material behavior: results are sorted by matchConfidence, matchConfidence is the fraction of query words found, and the downstream consequence that exerciseId drives automatic image/video resolution. It also warns against a failure mode (linking a wrong exercise's media), which no annotation conveys.

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?

Front-loaded with purpose and return shape, then the calling rule, then the fallback. Dense but nearly every clause carries operational value; the media-resolution sentence is slightly verbose but justifies itself by explaining why exerciseId matters.

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?

No output schema exists, and the description covers return shape (id, name, matchConfidence, sort order) plus the integration contract with create_workout_plan. The main omission is any statement about the limit parameter or expected result count, which matters for a search 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 0%, so the description must carry parameter meaning. It defines 'query' well — free-text interface, example, and how matching is scored — but the 'limit' parameter (default 8, max 20) is never mentioned, leaving a real gap.

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?

States a specific verb and resource: search the exercise catalog by free-text name, with a concrete example ('barbell squat'). It also clarifies the return is real catalog entries with ids, which separates it from a browse/list tool, though it never names the sibling browse_exercise_catalog as the alternative.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly prescribes when to call it ('for each exercise before create_workout_plan') and when not to trust the output (matchConfidence below ~0.7, or zero results → fall back to a plain name with no exerciseId). The decision rule is fully specified rather than implied.

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.