write_measurement

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

Adds substantial behavior beyond the annotations: the merge-or-replace-per-day semantics, that a null value removes a measurement (explaining the destructiveHint), unit defaulting and normalization to cm, and that a new custom name creates a kind. This is exactly the kind of detail annotations cannot convey.

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?

Front-loads the core operation and packs the important caveats (default date, one-per-day, null removal) early. The trailing enumeration of kinds is dense but necessary; sentences are long but not padded.

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?

For a mutation tool with nested objects, four parameters, and no output schema, the description covers the essential behavioral surface: date default, unit handling, custom kinds, and value kinds. It stops short of stating permissions or how the write relates to read_measurements/delete_measurement.

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 50%, and the description compensates by explaining unit defaults (app unit; cm, or in for a lb profile), storage in cm, bodyFat being a percentage, and the custom-name-to-kind mapping. It could still clarify the required-ness of date and the relationship between values and custom, but it adds real meaning.

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 verb and resource ('Log body measurements') plus the scope ('for a day'), which cleanly separates it from siblings like read_measurements, write_bodyweight, and delete_measurement. An agent can identify the operation without opening the schema.

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?

Gives clear operating context: defaults to today and one check-in per day, so a call merges into or replaces the day's entry. It never names sibling alternatives (e.g. write_bodyweight for weight-only), so routing guidance is implied rather than explicit.

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