get_sleep

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

Annotations already declare read-only, idempotent, non-destructive behavior, so the description's real contribution is the data-quality contract: missing fields read 'not recorded' and must never be coerced to zero, plus the informational-not-medical caveat. That is genuine behavioral context an agent could otherwise get wrong, though it says nothing about pagination or the 90-day limit (left to the schema).

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?

Three dense sentences with the resource and date-range scope front-loaded, followed by the caveats. Only the unexplained 'T2.' prefix and the redundant field list (already implied by the output schema) keep it from a 5.

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?

An output schema exists, so the field enumeration is arguably redundant, but the description supplies what the schema cannot: the missing-data semantics and the not-medical-advice framing. Combined with complete parameter docs and full annotations, an agent has enough 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% and both parameters are fully documented there, including the inclusive YYYY-MM-DD format and the 90-day cap. The description adds only the loose phrase 'over a date range' and no format or boundary detail, so the 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?

States a specific resource (per-night sleep) and enumerates the exact metrics returned (stages, score, HR, respiration, stress), which implicitly separates it from get_hrv and get_stress_and_body_battery. It never explicitly names a sibling it is not, and the leading 'T2.' token is unexplained noise, 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?

The domain makes usage fairly obvious, but there is no explicit statement of when to pick this over get_daily_overview or get_hrv, and no prerequisites. The only guidance given is interpretive ('not medical advice'), not routing guidance.

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