Skip to main content
Glama
Sign In
garmin-mcp

garmin-mcp

by wiande00
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

garmin_wellness

Read-only

Retrieve daily Garmin wellness metrics—sleep, HRV, body battery, stress, heart rate, steps—for a specified date to track health.

Instructions

One day of wellness data. summary: steps, calories, intensity minutes, resting/min/max HR, stress, body battery, SpO2, respiration, active and sedentary time. sleep: the night that ENDED on date (date=today is last night): times, stages, score, HRV, resting HR, SpO2. hrv: the same night's HRV, baseline and status. body_battery: charged/drained, high/low and the events that moved it. stress, heart_rate, steps: day totals plus an hour-by-hour profile. Also resting_hr, spo2, respiration, floors, hydration, intensity_minutes, events (auto-detected movement), lifestyle (lifestyle logging).

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_wellness"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateNoYYYY-MM-DD, 'today' or 'yesterday'today
detailNofull = Garmin's raw payload (large)summary
metricYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
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 interpretive context beyond that: it clarifies that the sleep/HRV payload is for the night that ENDED on `date`, and that detail=full is a large raw Garmin payload. It does not mention behavior for missing/absent data days, which would have made it a 5.

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 statement, then organized as a metric-keyed glossary, so an agent can scan to the relevant entry. The final sentence is a somewhat undifferentiated dump of metric names (floors, hydration, lifestyle) without explanation, which is mild filler.

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 only three parameters, a read-only annotation set, and no output schema, the description covers nearly everything an agent needs to call it correctly. The remaining gap is failure/empty-day behavior and whether date ranges beyond today/yesterday are supported, both left to the schema.

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 coverage is 67%, so the schema documents date, detail, and the metric enum mechanically. The description adds meaning the enum cannot: it explains what each metric value actually returns (e.g. stress/steps give day totals plus an hour-by-hour profile, events are auto-detected movement) and disambiguates the date parameter for sleep queries.

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 line names the resource and scope ('One day of wellness data'), and the per-metric breakdown makes the returned content concrete. It never contrasts itself with close siblings like garmin_body, garmin_trend, or garmin_status, so an agent must infer the boundary, which keeps it below a 5.

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 only implied through the metric inventory – an agent can guess that 'sleep' or 'body_battery' belongs here, but there is no explicit when-to-use or when-not statement and no pointer to an alternative for overlapping data such as body composition or trends. The one genuinely useful routing hint ('date=today is last night' for sleep) is semantic, not usage guidance.

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