Log a workout

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

Adds real behavior beyond the annotations: energy_kcal is stored as given and never computed, activity rows are immutable once logged, each call adds a row unless row_id is reused, and the row_id retry flow for failed adds. The closing 'data.ok says a re-read shows it' is cryptic and underspecified, which keeps this from a 5.

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 front-loaded sentences with the action and return value first, then semantics. Mostly tight, though the final sentence is dense and hard to parse, slightly weakening readability.

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 spell out return values and correctly focuses on mutation semantics and idempotency. The vague reference to 'data.ok' is the only loose end for a mutation tool with four required parameters.

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% so the baseline is 3, but the description adds meaning the schema lacks by explaining that energy_kcal is not derived and clarifying the row_id reuse/retry contract beyond what the property text already states.

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 a workout from the activity catalog') and immediately names the return value ('returns its row_id'). This clearly distinguishes it from add_food, search_activity and remove_activity without opening any 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?

Provides concrete routing context: get_today for date phrasing, search_activity for the catalog and energy semantics, and remove_activity + re-add for corrections. It never states exclusions against add_food explicitly, but the activity-vs-food boundary is self-evident from the naming and description.

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