garmin-mcp

Overview Schema Source Related Servers Discussions Admin

garmin_trend

Read-only

Retrieve daily or weekly values for a chosen Garmin health or training metric across a date range to analyze trends and compare changes over time.

Instructions

A metric across a date range, one row per day (or week). stats (steps + calories), steps, calories, stress, intensity_minutes, sleep (per night), hrv (per night), respiration, resting_hr, body_battery, weight, training_load (acute, chronic, ACWR, form per day), vo2max (the dates it changed), running_tolerance, endurance_score, hill_score, lactate_threshold, progress (activity totals by type). Most allow up to a year; respiration and daily stress/intensity minutes 31 days, training_load 90 days.

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": {
      "metric": "<metric>"
    },
    "name": "garmin_trend"
  }
}

Input Schema

Name	Required	Description	Default
`metric`	Yes
`end_date`	No	Last day, inclusive. Default today
`start_date`	No	First day. Default depends on the metric (2-13 weeks back)
`aggregation`	No	weekly works for steps, stress, intensity_minutes, running_tolerance	daily

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 4, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds real value beyond them by disclosing per-metric lookback ceilings and the granularity of the response (one row per day or week). It stops short of describing pagination, row count limits, or failure behavior when a range exceeds the cap.

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 behavior, then a dense metric catalogue, then constraints. The metric list largely echoes the enum but the parentheticals justify the space; a few clauses, such as the weekly-aggregation line, restate the schema.

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?

With no output schema, the description carries the burden of describing the return shape, and it does so (one row per day/week) while also covering date defaults and retention caps. It leaves the expected date string format unspecified, which is a small gap for a tool whose two date params are typed only as plain strings.

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 75%, so the baseline is 3, and the description earns that by expanding several enum values with meaning not present in the raw enum names (stats = steps + calories, training_load = acute/chronic/ACWR/form, vo2max = the dates it changed). The aggregation rule and the start_date default are already in the schema, so those statements duplicate structured data rather than add to it.

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 opening clause states a specific shape: one metric, over a date range, returned as one row per day or per week. That distinguishes it clearly from point-in-time siblings such as garmin_wellness or garmin_status, though no sibling is named explicitly.

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 retention window list ("Most allow up to a year; respiration and daily stress/intensity minutes 31 days, training_load 90 days"), which tells an agent what ranges are legal. However, it never explicitly says when to pick this tool over garmin_wellness, garmin_body, or garmin_training for the same data, so the agent must infer the routing.

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