fitbit_get_skin_temperature

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

With no annotations, the description discloses that values are relative deviations, not absolute temperature, and that baseline takes ~3 nights. It also describes the return structure (one entry per night with nightly_relative and log_type). Lacks details on error conditions or rate limits, but sufficient for most use cases.

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?

Efficiently structured: summary line, critical clarification, usage note, then parameter list. No redundant information; every sentence adds value.

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?

Despite having an output schema, the description explains the return format (nightly_relative and log_type). It also provides baseline establishment information and use-case context, making the tool well-understood.

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 description coverage is 0%, but the description fully compensates by explaining each parameter: start_date format options ('YYYY-MM-DD', 'YYYY-MM', or '30d'), end_date format, and the live parameter for cache bypass, including defaults.

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 clearly states the tool retrieves 'nightly skin temperature variation (degrees Celsius from personal baseline)', identifies it as a relative measurement, and distinguishes it from the sibling tool for absolute core temperature. It also lists use cases (illness/cycle/recovery signal).

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 states when to use (relative skin temp) and when not to (use fitbit_get_core_temperature for fever/body temp). Also notes that Fitbit needs ~3 nights to establish a baseline, guiding the agent on data availability.

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