garmin_sleep

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds no behavioral context beyond the annotations — it is purely a restatement of return fields, which the output schema already carries, and says nothing about missing nights, timezone handling, or data availability.

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?

One compact sentence with no filler, and the most important signal (per-night granularity) is front-loaded. The comma-separated field list is dense but readable.

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 explain return values, yet that is nearly all it does. It is adequate for a simple one-parameter read tool but omits any framing of scope, data gaps, or relationship to sibling health tools.

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 'days' parameter is fully documented in the schema (default 7, range 1-30). The description never references the lookback window, so it adds no meaning beyond the schema; baseline 3 applies.

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 enumerates the specific resource (per-night sleep metrics: score, duration vs sleep need, stage minutes, HR, HRV, stress, respiration, restlessness), which makes the tool's domain unmistakable. It lacks an explicit verb ('retrieve') and never distinguishes itself from overlapping siblings like garmin_readiness or garmin_body_metrics, so it stops short of a 5.

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?

There is no when-to-use guidance, no mention of the days window in prose, and no routing to or away from alternatives such as garmin_readiness. The agent must infer usage entirely from the field list.

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