Skip to main content
Glama
Sign In
garmin-mcp

garmin-mcp

by wiande00
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

garmin_create_workout

Build structured Garmin workouts with timed, distance, rep, or lap-button steps and targets, then save them to Garmin Connect for watch sync.

Instructions

Build a structured workout and save it to Garmin Connect (it syncs to the watch). Each step ends one way (duration, distance_km, reps or lap_button) and has at most one target (hr_zone, hr_bpm, pace_min_km, speed_kmh, power_w, power_zone, cadence). Strength steps name a catalog exercise. See the workout://templates resources. Confirm the plan with the user first.

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": {
      "name": "<name>",
      "sport": "<sport>",
      "steps": "<steps>"
    },
    "name": "garmin_create_workout"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYes
sportYes
stepsYesIn order. A step, or {repeat: n, steps: [...]}
descriptionNo
pool_length_mNoSwimming only
schedule_dateNoAlso put it on the calendar this day

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations only declare it is not read-only, not destructive and not open-world; the description adds the far more useful fact that the workout is persisted to Garmin Connect and pushed to the watch, plus hard structural invariants (one end condition, at most one target per step). It does not say what the response contains (e.g. a workout id) or what happens on name collisions.

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?

Front-loaded with purpose, then tight sentences on step rules, strength exercises, the templates resource and the confirmation guardrail. Every sentence earns its place; density is high but nothing is padding.

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?

For a tool with a nested Step/Repeat schema and no output schema, the description covers the construction contract and the safety guardrail well. Gaps are small: no guidance on scheduling versus later scheduling, nothing about what the call returns, and the sport/pool_length_m/schedule_date parameters are left entirely to the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With only 50% schema coverage, the description carries real weight: it explains the mutually exclusive end conditions, names the seven possible targets and the 'at most one' rule, and states that strength steps must use a catalog exercise name. Those constraints are not recoverable from the schema, which merely lists the fields as optional and nullable.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description uses a specific verb and resource — 'Build a structured workout and save it to Garmin Connect' — and adds the meaningful consequence that it syncs to the watch. It does not, however, state how it differs from the sibling tools garmin_upload_workouts or garmin_schedule_workouts, leaving the agent to infer that this one creates rather than uploads or schedules.

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?

'Confirm the plan with the user first' is an explicit workflow prerequisite, and 'See the workout://templates resources' routes the agent to an authority before composing steps. What's missing is when-not-to-use guidance against the closely named siblings (upload_workouts, schedule_workouts), so the routing context is clear but not exhaustive.

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

Deploy Server

Other Tools