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

Beyond the annotations (which only signal a non-destructive, non-idempotent write), it discloses the key traits an agent can't infer: the report is stored for Yenta's team, never shown publicly, and returns a reference. The "leave out personal details" instruction is genuine behavioral guidance. It does not say whether repeat submissions create duplicate reports or whether the report is ever answered conversationally.

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?

Two compact sentences, front-loaded with what to report, then the privacy/visibility constraints. No filler, and the most decision-relevant content (what counts as a report) comes first.

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?

The output schema covers the reference returned, and the description still flags it; annotations cover the safety profile; the privacy note covers the main misuse risk for an 8-parameter write tool. Remaining gap is small: nothing about duplicate submissions or any rate/abuse limit on a non-idempotent mutation.

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 parameters are already fully documented, and the description's category list largely restates the `kind` enum. The one addition is the privacy constraint ("leave out personal details"), which shapes what goes into `message` beyond the schema's length limit – real but marginal added meaning, so baseline 3 fits.

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 sentence pairs a specific verb ("Send ... a report") with the target (Yenta) and enumerates the exact report categories, which map cleanly onto the `kind` enum. The write nature makes it unmistakable against the read-only destination_*/venue_*/search_* siblings, though no sibling is named explicitly.

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?

"data that is missing or looks wrong, a tool that was hard to use, or anything else" gives concrete triggering conditions that align with the enum values. There are no exclusions, however – it never says what should NOT be reported here (e.g. ordinary search questions) or what the alternative channel is.

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