Sleep summaries

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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered. The description adds behavior the annotations cannot: the row-per-night grain, the wake-date keying convention, local-time boundaries, the 92-day cap, and that detail='full' returns Garmin's raw records.

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 what is returned, then sibling routing, then the call mechanics — a sensible information hierarchy for a dense definition. It is a long semicolon-chained sentence, but nearly every clause carries field or routing information rather than filler.

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?

There is no output schema, so the description carries the return-value burden — and it does so by naming the fields and units an agent needs to reason over results. Combined with the date-window limits and the detail toggle, an agent has everything required to call this correctly.

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%, so the baseline is 3, but the description adds interpretive meaning: dates are keyed to the day the user woke up (clarifying how the range maps to rows) and it restates the period-vs-dates choice with concrete period names. The distinction between compact and full payloads is reinforced rather than merely repeated.

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?

Names a specific resource (night-by-night sleep over a range) with an exact grain: one compact row per night keyed to the wake-up date. It enumerates the returned fields (duration, stages, score, HR/stress/respiration, SpO2, sleep need vs baseline) and explicitly differentiates itself from get_sleep, get_readiness and summarize_wellness.

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 explicit when-to-use routing: 'For last night alone use get_readiness or get_sleep; for trends over weeks or months use summarize_wellness.' It also states the operational rule — up to 92 days per call, pass a period or start_date/end_date — so an agent knows both scope and the alternative path.

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