Skip to main content
Glama

getActivitySets

Reads the strength training sets of one recorded activity, returning reps, weight, rest, muscles, and planned versus completed sets for per-exercise trends.

Instructions

Strength training sets of an activity, read from the original .FIT file. One entry per exercise, in the order first done, with its movement category, its primary and secondary muscles (from Garmin's exercise catalogue) and its active sets: reps, weight (kg, absent when none was recorded), set time in seconds and the rest after the set (restSec). Each exercise with weight also has top (the heaviest set of 1 to 12 reps, then the most reps; without one, the heaviest set) and e1rmKg (the best estimated 1RM, Epley, of its sets of 1 to 12 reps; null when it has none). Exercise names are stable across sessions, so they can be used for per-exercise trends. Edits made later in Garmin Connect (renamed exercises, corrected reps or weights) are not in the .FIT file. Use it for strength sessions; for runs, rides and swims use getActivityLaps. plan is the planned workout that the watch ran (null without one): its name and, per planned exercise and rep plan (a pyramid gives a row per rep plan) in plan order, plannedSets, plannedReps (low to high; high null is at least low), doneSets, reps, and verdict (hit or miss, why: sets or reps; extra and over count the done sets above the plan and above the high end); a warm-up or cool-down row (part) and a notInPlan row have verdict null. In a rest-pause group (a repeat of one exercise with a rest of 20 s or less inside it and a longer rest after it), only the first set of each pass is judged on reps. Such a row has restPause true. Each planned row also has plannedRestSec: the planned rests right after its sets, in seconds and plan order (null: an open rest, ended with the lap button; empty: no rest right after it, such as the first exercise of a superset).

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": "getActivitySets"
  }
}

Input Schema

NameRequiredDescriptionDefault
activityIdYesGarmin activity id

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.13.0

TDQS

A4.2/5.0
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 it does disclose provenance and staleness (data read from the original .FIT file, Garmin Connect edits missing) plus null semantics throughout. It stops short of stating what happens for a non-strength activity id or how large/expensive the response can be, so it is not fully complete.

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 purpose and routing are front-loaded, and much of the length is justified because no output schema exists to hold the return shape. However, it is a dense run-on block with deep parentheticals (e.g. the top/e1rmKg and restPause clauses) that would read far better as a structured list.

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, so the description must document the return structure, and it does so thoroughly — ordering, movement category, muscles, per-set fields, top/e1rmKg, plan rows and verdicts. The remaining gap is edge-case behavior (empty result, non-strength activity), which leaves it just short of complete.

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?

Only one parameter, fully documented in the schema as "Garmin activity id" (100% coverage). The description adds no additional meaning about that id — no format, no source hint beyond the sibling listActivities implication — so 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 and scope: strength training sets of an activity, read from the original .FIT file. It explicitly carves itself out from the sibling getActivityLaps ("for runs, rides and swims use getActivityLaps"), so an agent can route 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?

Gives both positive and negative routing: use for strength sessions, use getActivityLaps for runs/rides/swims. It also states a real usage caveat — later edits in Garmin Connect are absent from the .FIT source — which tells the agent when the data will be stale.

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