garmin_sleep

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, openWorldHint), so the bar is lower, and the description still adds two genuinely non-obvious behaviors: records are keyed to the wake-up date rather than the sleep-onset date, and the window is capped at 366 days with a 7-day default. It does not discuss pagination or payload size at the 366-day maximum, which is the main remaining gap for an open-world read.

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?

A single dense block with the field inventory front-loaded and the operational constraints (wake-up date keying, range cap, default window) trailing in two short clauses. Every clause carries information; there is no restatement of the tool name or filler framing.

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 an output schema present, the description needn't document return shapes, and annotations cover safety; the schema itself fully documents all three optional params. What remains thin is routing guidance among the sleep-related siblings, which is the only thing an agent could still get wrong.

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 description coverage is 100%, so the baseline is 3, but the description adds meaning the schema omits: it supplies the actual default of 7 days, a value the schema leaves unstated for `days`, and clarifies the 366-day ceiling that bounds `start_date`/`days`. Enum and format details (YYYY-MM-DD, local calendar) are left entirely to the schema, appropriately.

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?

The description names a specific resource and enumerates exactly what each record contains (bedtime, wake time, stage minutes, sleep score with sub-scores, HR, stress, SpO2, respiration, sleep need, feedback), so an agent knows this is raw per-night sleep data rather than an aggregate or coaching tool. It never names or contrasts with the sibling garmin_sleep_analysis, so the differentiation is inferred from content depth rather than stated.

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?

It gives concrete framing cues — 'Filed under the wake-up date', 'Range up to 366 days, default last 7' — which tell the agent how to interpret and size a request. It stops short of stating when to prefer this over garmin_sleep_analysis or when a single night vs. a range is appropriate, so usage is implied rather than prescribed.

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