Skip to main content
Glama
Sign In
garmin-mcp

garmin-mcp

by wiande00
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

garmin_fit_messages

Read-only

Decode and page FIT file messages for an activity with Garmin's SDK to answer questions other tools cannot.

Instructions

Every field of the activity's FIT file, decoded with Garmin's FIT SDK, paged. For questions no other tool answers.

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": {
      "activity_id": "<activity_id>"
    },
    "name": "garmin_fit_messages"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMessages per page, 1-5000
offsetNo
activity_idYes
message_typesNoe.g. session, lap, record, event, hrv, device_info. Default: all small ones
include_recordsNoAlso the per-second records (large)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already establish it as a read-only, non-external operation, and the description adds that output is paged and sourced from the official Garmin SDK. It does not say how large a typical response is, that per-second records are excluded by default (that lives only in the schema), or whether failures occur for activities lacking FIT files.

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?

Two short, front-loaded fragments with the core capability stated first and the routing hint second. Nothing is wasted, though the telegraphic style sacrifices some clarity for brevity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With five parameters, no output schema, and 60% schema coverage, the description should say more about what a returned 'message' actually looks like and how to page safely. The fallback framing is present but the practical invocation context for a raw-dump tool is thin.

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 60%, with limit, message_types, and include_records documented in the schema while offset and activity_id have no description at all. The description's 'paged' hints at limit/offset but adds no format or default behavior beyond what the schema already states.

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?

Names the specific verb and resource: it decodes every field of an activity's FIT file using Garmin's FIT SDK and pages the results. This clearly separates it from aggregate siblings like garmin_activity_analysis or garmin_activity, though the sibling it supersedes is never named outright.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The only usage guidance is the vague catch-all 'For questions no other tool answers', which gives a fallback condition but never names which tools to try first or what data categories it covers. An agent gets no concrete signal about when this beats garmin_activity or garmin_activity_analysis.

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