Skip to main content
Glama

listActivities

Read-only

Retrieve and compare Garmin activity summaries by date, type, or name to find activity IDs and review training metrics such as distance, pace, heart rate, and training load.

Instructions

List the user's Garmin activities (most recent first) as a compact summary: id, name, type, local start time, distance (km), moving duration, average pace, average/max heart rate, cadence, ascent; when Garmin has them: elapsed time (if longer than moving time), race flag, Garmin training load, aerobic/anaerobic training effect and label, seconds in HR zones 1-5, calories, moderate/vigorous intensity minutes, body battery change, steps, swim SWOLF, pool length, lengths and strokes, power, mountain-bike grit and flow, a ride's km/h, ascent per hour and easy (zones 1-2) and hard (zones 4-5) share of the zone time, running form (stride, ground contact, vertical oscillation and ratio), grade-adjusted pace, best efforts (1k, mile, 5k, 10k, half, marathon) and run/walk segments. Dates are yyyy-MM-dd. Set raw=true for Garmin's full JSON. limit is at most 200; names filters the last 200 activities of the date window. Use it to find activity ids and to compare many activities. For the laps, sets or plan of one activity, give its id to getActivityLaps, getActivitySets or getActivityWorkouts.

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": "listActivities"
  }
}

Input Schema

NameRequiredDescriptionDefault
rawNoReturn Garmin's raw JSON instead of the summary
limitNoMax number of activities, default 20
namesNoActivity names (optional): keep only the activities whose name contains one of them, ignoring case
endDateNoEnd date yyyy-MM-dd (optional)
startDateNoStart date yyyy-MM-dd (optional)
activityTypeNoActivity type key (optional): a parent type such as running or cycling, or a subtype such as trail_running

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.13.0

TDQS

A4.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds genuinely useful behavior: results are capped at 200 and 'names' only filters the last 200 activities of the date window, which an agent could not infer elsewhere. However, it never states the default page size (20, only in the schema) or what happens when filters match nothing, so disclosure is partial for a broad listing call.

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?

Purpose and alternatives are correctly front-loaded and back-loaded around the core content, but the middle is a sprawling multi-clause enumeration of every possible return field (SWOLF, grit and flow, best efforts, run/walk segments) that an agent rarely needs to select the tool. The size is justified only because there is no output schema; as prose it is dense and hard to scan.

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 field enumeration is the only place return content is disclosed, and combined with the filter/limit rules and sibling routing this is nearly complete for a 6-parameter listing tool. The remaining gap is the omitted default limit and any statement about empty-result behavior.

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 100%, so baseline is 3, and the description clearly earns above baseline by adding the hard 200 cap on limit and the scoping rule that name filtering applies only within the last 200 activities of the date window — neither is expressible from the schema. It largely restates the date format and raw behavior already documented per-parameter.

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?

Opens with a specific verb and resource plus scope and ordering: 'List the user's Garmin activities (most recent first) as a compact summary.' It then names the exact siblings that handle per-activity detail (getActivityLaps, getActivitySets, getActivityWorkouts), so an agent can separate list-level from detail-level calls without opening a schema.

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?

'Use it to find activity ids and to compare many activities' gives positive guidance, and the closing sentence gives the exclusion plus the alternative to use instead. The 'raw=true for Garmin's full JSON' note also tells the agent when the compact default is insufficient.

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