garmin-mcp

Overview Schema Source Related Servers Discussions Admin

garmin_upload_workouts

Upload Garmin workouts written in JSON after validating IDs, targets, repeat groups, and power settings to prevent invalid uploads.

Instructions

Upload workouts written directly in Garmin's JSON. All are checked before any is uploaded (ids vs keys, nested targets, power targets, repeat groups). Prefer garmin_create_workout unless the exact JSON matters.

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": {
      "workouts_json": "<workouts_json>"
    },
    "name": "garmin_upload_workouts"
  }
}

Input Schema

Name	Required	Description	Default
`workouts_json`	Yes	Garmin workout JSON objects (garmin_workouts raw=true shows the format)

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 4, 2026

TDQS

A4/5.0

Behavior3/5

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

Annotations already declare this is a non-read-only but non-destructive, closed-world write. The description adds real behavioral value by disclosing all-or-nothing validation ("All are checked before any is uploaded") and the categories of checks (ids vs keys, nested/power targets, repeat groups). It does not say what is returned on success, whether existing workouts are affected, or how validation failures surface.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with purpose, then validation behavior, then the sibling routing rule. No filler or redundancy.

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 one-parameter write tool with no output schema, the description covers format source, validation/atomicity, and the alternative tool. Return values and failure surfacing are left unstated, which is a modest gap.

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?

Schema coverage is 100% and the single parameter already documents that these are Garmin workout JSON objects with a pointer to garmin_workouts raw=true for the format. The description confirms the expected dialect and enumerates validated constructs, but adds no new shape or field syntax beyond the schema.

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?

States a specific verb and resource ("Upload workouts") plus the required input format ("written directly in Garmin's JSON"), and explicitly contrasts itself with the sibling garmin_create_workout, so an agent can pick between them without opening the schema.

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 an explicit routing rule: "Prefer garmin_create_workout unless the exact JSON matters." That covers the main alternative and the condition selecting this tool, but no other context (bulk use, prerequisites, auth/account needs) is mentioned.

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