Sleep (nightly summary)

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

Annotations already declare readOnlyHint/idempotent/non-destructive, so safety is covered; the description adds real value beyond them with the day-labelling convention and the range cap of 366 days. It does not disclose what happens when no device/data exists for a night, which is the main remaining 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.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the source and contents, then defaults and limits in a short trailing sentence. The metric list is long but each item is informative for an agent deciding whether this is the right tool; no filler sentences.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description responsibly enumerates the returned fields, and it states defaults, range cap, and date semantics. Missing only edge-case behavior (missing nights, multiple devices, per-night vs aggregated) for a full 5.

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

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

Schema coverage is 100% with per-param descriptions, so baseline is 3; the description adds a constraint not present in the schema (maximum 366-day span) and corroborates the 7-day default. That is modest but genuine added meaning over the schema.

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

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

Specific verb+resource ('Nightly sleep from a Withings sleep mat or watch') with an explicit enumeration of the metrics returned (total sleep, time in bed, stage minutes, efficiency, latency, score, HR/BR, snoring, disturbances). This clearly separates it from siblings like get_body_measurements, get_blood_pressure, and get_daily_activity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

Gives concrete defaults (last 7 days) and an explicit ceiling (up to 366 days), plus the non-obvious rule that a night is labelled by the day it ends. It doesn't explicitly name alternatives or when-not to use it, but the domain boundary against the other health-data siblings is evident.

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