garmin_hrv

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

Annotations already declare readOnly, idempotent, and openWorld, so the safety profile is covered. The description adds substantive behavior beyond that: the exact payload fields, the enumerated status values (BALANCED/UNBALANCED/LOW/POOR), the 366-day ceiling, and the 14-day default window — all useful for predicting what comes back.

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?

Two sentences, front-loaded with what the tool returns, followed by range/default constraints. No filler. The metric enumeration is dense but each item carries information; a minor cost is that the enum list of statuses sits mid-sentence rather than in its own clause.

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?

For a read-only three-parameter query tool with a full output schema and complete annotation coverage, nothing essential is missing. Return fields, status values, window bounds, and defaults are all conveyed, leaving no ambiguity that would cause a mis-call.

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 would be 3. The description nonetheless adds meaning the schema lacks: the 366-day maximum and the 14-day default for the `days` window, which the schema only describes abstractly as 'number of days ending at end_date'. It does not clarify precedence between start_date and days beyond what the schema says.

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 the specific resource (per-night HRV in ms) and enumerates the exact metrics returned: last-night average, 5-minute high, 7-day average, baseline band, and Garmin status. This clearly separates it from siblings like garmin_heart_rate or garmin_sleep, though it never explicitly names an alternative or states the verb 'retrieve'.

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?

Usage is implied rather than stated: the agent can infer this is the HRV-specific query, and the 'Range up to 366 days, default last 14' line gives a practical bound. There is no explicit when-to-use/when-not guidance or routing to a sibling such as garmin_recovery_status for interpretation.

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