Skip to main content
Glama
kavakoss

mcp-garmin-connect

by kavakoss

download_activity_file

Download the original Garmin activity ZIP with the raw .FIT file for a given activity ID, preserving GPS, heart rate, cadence, and lap data for detailed analysis.

Instructions

Download the original activity file (ZIP containing the .FIT) for one activity.

Personal API only. This is the raw recording — GPS track, HR, cadence, laps, sample by sample — which the unofficial flow cannot fetch. Garmin strips some fields it computes (VO2 Max, recovery time, performance condition) from files delivered through its API, so this is not identical to a manual download.

Input Schema

NameRequiredDescriptionDefault
save_pathNoWhere to write the .zip. Empty = activity-<id>.zip in cwd.
activity_idYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.4.0

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does well: it discloses the API tier requirement, the delivered format, and a non-obvious fidelity caveat (Garmin strips VO2 Max, recovery time, performance condition). It does not mention that the call writes a file to disk or any size/latency characteristics, which is the main remaining gap for an unannotated tool.

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 the core action and artifact, then supporting caveats in short clauses. Every sentence carries information, though the 'sample by sample' enumeration is slightly decorative.

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?

An output schema exists, so return values need not be explained; the description covers purpose, auth tier, format, and fidelity caveats. The one omission is the write-to-disk side effect implied by save_path, which matters for a file-producing tool with no annotations.

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 50%: save_path is well documented in the schema, but activity_id has no schema description. The description's 'for one activity' partly compensates for activity_id, and its silence on the save_path/filesystem behavior leaves that side effect to the schema alone. Baseline 3 is appropriate.

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 ('Download the original activity file') and pins down the exact artifact ('ZIP containing the .FIT') plus scope ('for one activity'). This is clearly distinguishable from siblings like get_activity_detail, which return processed JSON rather than the raw file.

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?

'Personal API only' and 'which the unofficial flow cannot fetch' tell the agent the precondition and why this tool exists rather than an alternative. It never explicitly names a sibling or a when-not-to-use case, so routing is strongly implied but not spelled out.

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