get_sleep

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

Describes keying logic (morning wake-up date), error behavior, and declares read-only. No annotations provided, but description carries full burden adequately.

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?

Single dense sentence with all essential information, front-loaded with return structure. No unnecessary words.

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?

Fully covers purpose, usage, parameters, errors, and prerequisites. No output schema needed as fields are described. Complete for a single-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 covers 100% of parameter description. Description adds important context: keyed to morning, sync frequency, reliability note, enhancing agent understanding.

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?

Clearly states it returns a sleep summary for one night keyed by wake-up date, listing specific fields. Differentiates from sibling list_sleep by noting list_sleep is for date ranges.

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?

Explicitly tells when to use (single night) and when not (use list_sleep for range). States prerequisites (Sleep API subscription) and error conditions (SuuntoNotFoundError, 404).

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