Skip to main content
Glama

getActivityLaps

Retrieve per-lap splits and details from a Garmin activity's FIT file, including pace, heart rate, cadence, power, workout steps, and swim sets for interval analysis.

Instructions

Laps of an activity as recorded by the watch (manual laps, auto-lap every km, or workout steps), read from the original .FIT file. One row per lap: distance (km), timer time, pace (min/km, foot sports) or speed (km/h), average/max HR, cadence (spm for running), ascent/descent, average power, running form (gctMs, vertRatioPct, vertOscCm, strideCm), intensity (active, interval, rest, recovery, warmup, cooldown; the auto laps of a free run can be interval), lap trigger, and the step of the planned workout (step: the reps of one drill share it). A swim lap also has metres, swimPace (per 100 m), stroke, lengths, swolf and strokes. Use it for intervals and per-km splits; getActivity does not have them. For a run: split (pace of the first and second half, kind, hrDriftPct) and, for a structured workout, work (reps, pace, avgHR, and the fade of each step with more than one rep, pct). For a swim: sets, the laps in a row of one distance, stroke and intensity (reps, firstPace, lastPace, pct: above 0 is slower, firstSwolf, lastSwolf). null is n/a. For a run, plan is the planned workout that the watch ran (null without one): its name and, per lap with a step in lap order, the step's target (type, low, high, unit; or zone), done (the lap in that unit), verdict (hit inside the target, ends included, or miss) and off (how far outside, in the unit: s/km for pace, above 0 is slower). An open or zone target, a target in %max or %ftp, a target outside a plausible range, a lap under 15 m or 8 s or a lap without the value has verdict null.

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": {
      "activityId": "<activityId>"
    },
    "name": "getActivityLaps"
  }
}

Input Schema

NameRequiredDescriptionDefault
activityIdYesGarmin activity id

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.13.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does so well: it discloses the source file, the per-lap field set, per-sport variations, null semantics, and the exact null-verdict conditions (open/zone targets, %max/%ftp targets, laps under 15 m or 8 s). It stops short of 5 because it says nothing about lap count limits, ordering guarantees, or failure behavior for activities with no laps.

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 core purpose and the getActivity contrast are front-loaded, which is good, but the body is an extremely dense run of run-on sentences enumerating dozens of field names, including conditional per-sport branches. Much of that field enumeration could be trimmed or structured; each sentence carries information, but the wall-of-text delivery hurts scannability.

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?

Because there is no output schema, describing the return shape is essential and the description does it thoroughly for run, swim and workout cases. The remaining gap is operational: nothing on how many laps can return, what an empty result looks like, or error handling.

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?

The single activityId parameter is fully documented in the schema (100% coverage) as 'Garmin activity id', and the description adds no further meaning such as where to obtain that id. With the schema doing the work and only one parameter, the 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?

Opens with a specific verb+resource ('Laps of an activity as recorded by the watch') and states the data source (the original .FIT file) and the granularity (one row per lap). It explicitly distinguishes itself from sibling getActivity ('getActivity does not have 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?

Gives a clear use case ('intervals and per-km splits') and names the alternative it beats (getActivity), which is exactly the routing decision an agent faces. It falls short of a full 5 because it never states when not to use it, e.g. for activities without laps or when only summary totals are needed.

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