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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety bar is covered. Beyond that, the description adds two genuinely useful traits: stages are only present "when available" (variable response shape) and every response may carry serviceAnnouncements that must be surfaced distinctly to the user — a non-obvious obligation no annotation conveys.

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 the read action and followed by the response-handling obligation; no filler. The announcements sentence is slightly verbose but carries information that would otherwise be lost.

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 carries some burden of describing the return; it names sleep stages and discloses the announcement field, which covers the essentials. The remaining gap is the behavior when date is not supplied, which an agent would need to know for this optional-parameter tool.

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% and the single date parameter is fully documented as YYYY-MM-DD in the schema, so baseline 3 applies. The description adds nothing beyond "for a date" — notably it does not say what happens when the optional date is omitted (required list is empty), which is the one semantic gap.

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 states a specific verb and resource ("Read ... Garmin sleep details for a date") and adds scope ("including stages when available"). It implicitly separates itself from the history sibling by asking for a single date, but never names that sibling, so an agent must infer the split.

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 only implied by "for a date" — an agent can infer this retrieves one night's detail versus garmin_get_sleep_history for ranges, but the description never says so explicitly and gives no when-not guidance. The second sentence addresses post-call behavior, not tool selection.

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