Skip to main content
Glama

get_sleep

Read-onlyIdempotent

Retrieve nightly sleep data over a date range, including hours, sleep stages, score, heart rate, respiration, and stress, to review Garmin-recorded sleep patterns.

Instructions

T2. Sleep per night over a date range: hours, deep/light/REM/awake minutes, sleep score, Garmin's feedback, average heart rate, respiration and sleep stress. Each night is labelled woke_up_on, the morning it ended. Results are informational, not medical advice. Fields Garmin did not record say 'not recorded'; never treat them as zero.

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": {
      "start": "<start>",
      "end": "<end>"
    },
    "name": "get_sleep"
  }
}

Input Schema

NameRequiredDescriptionDefault
endYesLast date, YYYY-MM-DD (inclusive); at most 90 days after start.
startYesFirst date, YYYY-MM-DD (inclusive).

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already establish it as a safe, idempotent read, and the description adds real behavioral substance beyond them: each night is keyed by 'woke_up_on' (the morning it ended), missing fields return 'not recorded' and must never be treated as zero, and results are informational not medical. It does not discuss limits (the 90-day cap lives only in the schema) or volume/pagination behavior.

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-loads the resource and returned fields, then follows with the semantic caveats in priority order; every sentence carries information. The leading 'T2.' tag is unexplained noise that does not help the agent.

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 an output schema, full parameter docs, and read-only annotations available, the description supplies the remaining pieces an agent needs: what each night represents, how missing data is signalled, and the non-medical framing. The only shortfall is the absence of routing guidance against overlapping siblings.

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 description coverage is 100%, with both start and end formats plus the 90-day maximum already documented in the schema. The description only restates 'over a date range' and adds no syntax or constraint detail beyond that, so the baseline of 3 applies.

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?

States a specific resource and granularity ('Sleep per night over a date range') and enumerates the returned dimensions (hours, sleep stages, score, HR, respiration, stress), which cleanly separates it from siblings like get_hrv and get_stress_and_body_battery. An agent can pick this without opening the schema.

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 by the description of the data returned; there is no explicit 'use this when...' guidance, no exclusions, and no reference to overlapping siblings such as get_daily_overview or compare_periods. The date-range wording implies a per-window retrieval pattern but leaves selection to inference.

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