Skip to main content
Glama

getActivityWorkouts

Read-only

Retrieve the planned workout an activity followed, including ordered steps, intensity, duration, targets, strength exercises, and coach notes. Use it to inspect the full plan when an activity has one.

Instructions

The planned workout that an activity followed, as created in Garmin Connect: its steps in order, each with its intensity (warmup/active/rest/recovery/cooldown), its duration (time in seconds, reps, or open), its target (cadence, heart rate, pace, or open, with low and high values), the exercise for strength steps, and the coach's notes. A step with durationType REPEAT_UNTIL_STEPS_CMPLT repeats the steps from stepIndex durationValue up to it, targetValue times in all. Use it for the whole plan and its notes. For plan against done (hit or miss), read the plan field of getActivitySets (strength) or getActivityLaps (runs) instead; a ride or a swim has no plan field. An empty list means the activity followed no planned workout. Null fields are left out.

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": "getActivityWorkouts"
  }
}

Input Schema

NameRequiredDescriptionDefault
activityIdYesGarmin activity id

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.13.0

TDQS

A4.3/5.0
Behavior4/5

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

The annotations already establish that this is a read-only operation, and the description adds behavior they cannot convey: an empty list means no planned workout was followed, absent fields are nulls that were omitted, and the repeat step expansion rule. It does not mention error behavior for an invalid activityId or any rate limiting, so it stops just short of fully transparent.

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?

The content is front-loaded: the first sentence identifies the payload and then enumerates its parts. Every sentence adds information (repeat semantics, sibling routing, empty-list meaning, null omission), but the opening sentence is a very long clause stack that takes work to parse.

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 description does the heavy lifting by describing the returned structure, its nested target fields, and the repeat-step rule, which is unusually complete. The remaining gaps are minor: it does not state the top-level response shape (an array versus an object) or how a bad activityId is reported.

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?

There is a single required parameter, activityId, and the schema already documents it at 100% coverage ('Garmin activity id'). The description adds no syntax, format, or sourcing detail about that parameter, which is acceptable because the schema carries the burden, but it is the baseline rather than added value.

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?

It states a precise resource and scope: the planned workout an activity followed, with each step's intensity, duration, target, exercise, and coach's notes. It even explains the REPEAT_UNTIL_STEPS_CMPLT expansion, so an agent knows exactly what data comes back. It explicitly distinguishes itself from getActivitySets and getActivityLaps by assigning the plan-versus-actual comparison to those siblings.

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?

It gives an explicit when-to-use ('Use it for the whole plan and its notes') and a when-not-to-use, naming getActivitySets for strength and getActivityLaps for runs, plus the caveat that rides and swims have no plan field. It also states the empty-list semantics and that null fields are omitted, leaving little to infer.

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