garmin-mcp

by konstantintutsch

Overview Schema Source Related Servers Discussions Admin

Python

Local

get_goals

Read-only

Retrieve Garmin Connect goals filtered by active, future, or past status, with pagination controls for start and limit.

Instructions

Return goals by status (active, future or past). :param status: Status of goals (valid options are "active", "future", or "past") :type status: str :param start: 1-based index of the first goal to retrieve :type start: int :param limit: Pagination limit when retrieving goals :type limit: int :return: list of goals in JSON format. (Garmin Connect, read-only. Dates are YYYY-MM-DD.)

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_goals"
  }
}

Input Schema

Name	Required	Default
`limit`	No
`start`	No
`status`	No	active

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 27, 2026

TDQS

A3.5/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so safety is covered. The description adds the return format (JSON list) and date format (YYYY-MM-DD), plus that pagination is supported, but it omits defaults (status defaults to 'active', start=1, limit=30), maximum limits, and whether results are ordered.

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

Conciseness3/5

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

The core purpose is front-loaded, but the text is polluted by Sphinx docstring artifacts (':param status:', ':type status: str'), which duplicate type information already in the schema and make the description longer than necessary. It remains readable but not tightly edited.

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?

The tool has an output schema, so return values needn't be explained in depth, and annotations cover safety. The description documents all three parameters and the return format, making it nearly complete; only default values and pagination limits are missing.

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

Parameters4/5

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

Schema description coverage is 0%, so the description carries the burden and does so well: it enumerates valid status options, explains start as a 1-based index, and clarifies that limit is a pagination limit. It still omits the default values that appear in the schema, which would help an agent call it without surprises.

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?

The description opens with a specific verb and resource ('Return goals by status') and immediately names the three valid status values, so an agent knows exactly what is retrieved. It doesn't differentiate from siblings, but no sibling appears to retrieve goals, so the gap is minor.

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

Usage Guidelines3/5

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

Usage is implied by the status filter (active, future, past), which suggests when to call it, but there is no explicit guidance on when-not to use it or which alternative sibling to choose for other goal-related data. Minimum viable guidance.

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

Deploy Server