Skip to main content
Glama
Garmin Health MCP

Garmin Health MCP

by EmilbMadsen

get_sleep

Read-only

Retrieves a full sleep record for one night using the wake-up date, including stages, score, heart rate, SpO2, respiration, stress, and sleep need.

Instructions

Full sleep record for one night (the date the user woke up): sleep and wake time, time in deep/light/REM/awake, sleep score with per-factor ratings and optimal ranges, average heart rate, SpO2, respiration, sleep stress, awake count, and sleep need for today and tomorrow.

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_sleep"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateNoDate as YYYY-MM-DD in the user's time zone. Leave empty for today.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. Beyond that the description only adds the wake-up-date convention and a field inventory, without saying anything about historical data limits, missing-night behavior, or how scores are computed — useful but not rich behavioral context.

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?

A single front-loaded sentence with the grain stated first and the field inventory after; every clause is on-topic. It is long and partially duplicates the output schema's field list, which keeps it from a 5.

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 a one-optional-param read tool with an output schema and read-only annotations, the definition covers purpose, date semantics, and return scope. Nothing needed to call it correctly is absent; the only shortfall is the lack of guidance versus sibling sleep tools.

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 an extra point by clarifying that the date refers to the morning the user woke up, which resolves a genuine ambiguity about which night's record is returned — information the schema does not carry.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb+resource ("Full sleep record for one night") and immediately pins down the resource's grain with the parenthetical "the date the user woke up", which separates a single-night record from the aggregate siblings like get_sleep_summaries. The field enumeration further confirms what 'full record' means.

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: "for one night" and "Leave empty for today" tell the agent this is a per-night lookup, but the description never states when to prefer it over get_sleep_summaries or other sleep-related siblings, and gives no exclusions or data-availability caveats.

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