Garmin MCP for macOS

Overview Schema Source Related Servers Discussions Admin

garmin_api_daily_summary

Read-only

Retrieve a full daily Garmin Connect summary with all raw fields preserved. Query a single date or up to 31 days to analyze health and activity data.

Instructions

Full daily user summary, preserving all Garmin fields. Raw JSON fields are not normalized. Date ranges default to 7 days and allow at most 31 days (activity search uses pagination).

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": "garmin_api_daily_summary"
  }
}

Input Schema

Name	Required	Description	Default
`calendar_date`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Oct 26, 2026

TDQS

A4.1/5.0

Behavior5/5

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

The description explicitly states that 'Raw JSON fields are not normalized.' This is a crucial behavioral trait that goes far beyond the simple read-only annotation, alerting the AI that the output will be complex and potentially requiring specific parsing steps. This adds immense value over the structured metadata provided.

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?

The description is extremely efficient. It leads with the primary purpose (full summary) and immediately follows with critical operational constraints (default range and maximum range). Each sentence adds vital information.

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 description is highly complete for a comprehensive API summary tool. By detailing that fields are preserved exactly as raw JSON without normalization, it gives the agent a full picture of the data format and expectations for the output, compensating for the lack of an explicit output schema.

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?

Since schema description coverage is 0%, the description relies on context. It does not explain the semantics of the `calendar_date` parameter itself, but the surrounding text sets the overall context of date range constraints (7-31 days) that the input parameter relates to.

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 tool clearly identifies its function as providing a 'Full daily user summary,' defining the resource type. While it doesn't explicitly name a specific sibling it differs from, the emphasis on a 'full summary' suggests it provides a more comprehensive, all-encompassing dataset than singular metric tools like activity or sleep summaries.

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?

It provides specific usage boundaries by stating date ranges default to 7 days and have a maximum limit of 31 days. Furthermore, it directs the user toward a different tool for very large date searches, noting that 'activity search uses pagination.'

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