GarminMCP

list_recent_activities

Retrieve recent workouts with distance, duration, heart rate, pace or power, elevation, calories, and Training Effect. Filter by sport and date range to review training consistency and session load.

Instructions

List recent workouts with distance, duration, HR, pace/power, elevation, calories, and Training Effect.

Coaching Purpose: Provides a scannable training log across running, cycling, swimming, strength, and cardio sessions. Supports filtering by workout type and date range to inspect training consistency, session load distribution, and recent activity IDs for deep-dives.

Args: limit: Maximum number of activities to return (default 10). activity_type: Optional sport filter (e.g., "running", "cycling", "strength"). start_date: Optional start ISO date (YYYY-MM-DD) filter. end_date: Optional end ISO date (YYYY-MM-DD) filter. response_format: Output representation: "markdown", "json", or "hybrid" (default).

Returns: Formatted activity log containing activity IDs, distances, durations, average/max HR, pace/power, elevation gain/loss, calories, and aerobic/anaerobic Training Effect.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "list_recent_activities"
  }
}

Input Schema

Name	Required	Default
`limit`	No
`end_date`	No
`start_date`	No
`activity_type`	No
`response_format`	No	hybrid

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 12, 2026

TDQS

A4.2/5.0

Behavior3/5

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

No annotations are provided, so the description carries the full behavioral burden. It does disclose the return content and the default response format, but says nothing about read-only safety profile, result caps, ordering (newest first?), or what happens when filters match nothing - meaningful gaps for a tool with zero 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.

Conciseness5/5

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

Front-loads the core action in one sentence, then uses labeled sections (Coaching Purpose, Args, Returns) so an agent can jump to parameters. No filler sentences; each block adds distinct information.

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?

Covers purpose, filter semantics, defaults, and output shape for a five-parameter list tool. Since an output schema exists, the Returns block is partly redundant, but the one genuine gap is ordering and pagination behavior for a 'recent' listing.

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 0% schema description coverage, the description compensates well: it documents limit's default of 10, gives example activity_type values, specifies the YYYY-MM-DD ISO format for both date params, and lists the three response_format options with the default. It does not clarify whether the date range applies to activity start time or whether limit is applied before or after filtering.

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 ('List recent workouts') and enumerates the payload fields returned (distance, duration, HR, pace/power, elevation, calories, Training Effect). It also frames the scope as a scannable log versus deep-dives, which implicitly separates it from get_activity_details.

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 Coaching Purpose section gives concrete use contexts: inspecting training consistency, session load distribution, and grabbing activity IDs for deep-dives. It lacks explicit when-not guidance or a named alternative, so an agent must infer that get_activity_details is the deep-dive route rather than being told.

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

Deploy Server