Skip to main content
Glama
garmin-connect-mcp

garmin-connect-mcp

by Samiu1

Get Health Trend

garmin_get_health_trend
Read-onlyIdempotent

Fetch one Garmin health metric across a date range to track trends and compare changes in steps, sleep, HRV, body battery, weight, stress, hydration, or daily summaries.

Instructions

Get one health metric as a series across a date range, for trends and comparisons.

One metric per call keeps the response bounded. Metrics: steps, stress, hydration, daily_summaries (full daily wellness rollup), sleep (nightly summaries), hrv (daily HRV summaries), body_battery, weight (one entry per day), weight_all (every weigh-in), weight_goals.

Examples:

  • "Step trend this month" -> metric="steps", start_date="2026-11-01", end_date="2026-11-13"

  • "Has my sleep improved?" -> metric="sleep", start_date="2026-10-01", end_date="2026-11-13"

  • "All weigh-ins this year" -> metric="weight_all", start_date="2026-01-01", end_date="2026-11-13"

An empty result means no data in that range, not zero values. Narrow the range if the response hits the character limit.

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>",
      "start_date": "<start_date>"
    },
    "name": "garmin_get_health_trend"
  }
}

Input Schema

NameRequiredDescriptionDefault
chunksNobody_battery only: intervals per day; each reports its lowest and highest reading
metricYesWhich single metric to fetch across the range
end_dateNoLast date in range, inclusive, YYYY-MM-DD. Defaults to today.2026-11-15
start_dateYesFirst date in range, inclusive, YYYY-MM-DD
detail_levelNo'summary' keeps the headline figures and omits raw per-sample series, which is 90%+ smaller; 'full' returns everything Garmin sends, including every readingsummary
response_formatNo'markdown' for readable text, 'json' for the exact Garmin field names and valuesmarkdown
include_empty_fieldsNoKeep fields Garmin returned as null or empty. Off by default, since unsupported sensors on the user's device produce large runs of nulls. Turn on only to inspect raw shape.
include_all_weigh_insNoweight only: include every entry per day rather than the latest

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.0.2
    • changedInput schema / properties / end_date / default
      Previous value: -"2026-11-13"New value: +"2026-11-15"
  2. First observedv1.0.1

TDQS

A4/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open world), so the description's job is to add behavior, and it does: an empty result means no data rather than zero values, and responses can hit a character limit that argues for a narrower range. It still doesn't characterize the response shape or paging/truncation behavior in any detail.

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 purpose, then the metric catalog, then examples, then the two failure-mode gotchas — a sensible order. The metric list partially duplicates the schema enum and the three examples are slightly more than strictly needed, but nothing is 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?

For an 8-parameter read tool with no output schema, the definition covers the essentials: what one call returns (a bounded single-metric series), what an empty result means, and how to react to oversized responses. It leaves the actual response structure to inference, which is the main remaining gap.

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 100%, so the baseline is 3; the description earns above that by disambiguating enum values the schema only names — daily_summaries as a "full daily wellness rollup", sleep as "nightly summaries", weight as "one entry per day" versus weight_all as "every weigh-in". The examples also pin down the YYYY-MM-DD date format in practice.

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?

"Get one health metric as a series across a date range, for trends and comparisons" names a specific verb, resource, and scope, and the metric list makes the coverage concrete (daily rollups, sleep, HRV, weight variants). It does not explicitly say how it differs from the sibling garmin_get_daily_health, even though the daily_summaries metric appears to overlap with it.

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?

The three worked examples map plain-language requests to exact metric/date arguments, which is strong selection guidance, and "one metric per call" sets a clear usage constraint. It stops short of exclusions, e.g. when to prefer garmin_get_daily_health or garmin_get_raw over this tool for a single day or raw payloads.

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