Cronometer MCP

log_sleep

Idempotent

Record nightly sleep, including deep, light, and REM stages plus a score, in Cronometer to track trends and later edit or remove entries.

Instructions

Record a night's sleep, optionally with its stages and a sleep score.

Each value is stored as its own biometric (Sleep, and the Deep, Light, REM and Score metrics when the account has them), so they show in Cronometer's trends. Fix or remove one with edit_biometric or remove_biometric.

Args: hours: Total sleep in hours, e.g. 7.5. date: The diary day it belongs to, as YYYY-MM-DD (defaults to today). deep_hours: Deep sleep in hours. light_hours: Light sleep in hours. rem_hours: REM sleep in hours. score: Sleep score from 0 to 100.

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": {
      "hours": "<hours>"
    },
    "name": "log_sleep"
  }
}

Input Schema

Name	Required	Description	Default
`date`	No
`hours`	Yes
`score`	No
`rem_hours`	No
`deep_hours`	No
`light_hours`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv2.1.0Nov 14, 2026

TDQS

A4.4/5.0

Behavior4/5

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

The annotations already declare idempotentHint=true, destructiveHint=false and openWorldHint=true, and the description goes beyond them by disclosing the storage model: each value becomes its own biometric (Sleep, Deep, Light, REM, Score) so it surfaces in trends. It also warns that the stage and score metrics only exist when the account supports them. It does not state what happens to a prior entry on a re-logged date, which is the one behavioral gap.

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?

It is front-loaded with the action and storage behavior, then a compact Args block, with no filler sentences. The Args block restates the schema property names, but given 0% schema coverage that repetition is doing necessary work rather than padding.

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 six-parameter write tool with an output schema already covering return values, the description supplies the storage semantics, defaults, ranges and the repair path. The only meaningful omission is overwrite-versus-merge behavior when a night is logged twice for the same date, which matters for a tool the annotations mark idempotent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden and does: it gives units and an example for hours (7.5), the exact date format YYYY-MM-DD with the today default, the meaning of each stage parameter, and the 0-100 bound on score. Every one of the six parameters gains meaning that the bare schema titles do not convey.

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?

The opening sentence names a specific verb and resource (record a night's sleep) plus its optional scope (stages and a sleep score). It also implicitly separates itself from the generic biometric tooling by noting that later fixes go through edit_biometric or remove_biometric, so an agent can tell what this tool is for 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 Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is clear: this is the logging entry point, and corrections or deletions are explicitly routed to edit_biometric and remove_biometric, two named siblings. What is missing is any exclusion relative to add_biometric, which an agent might otherwise reach for when recording sleep-derived metrics.

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

Deploy Server