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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile needs no restating. The description adds non-annotation context: results are ranked personalized picks that each carry a stated rationale, which tells the agent what the response items look like. No mention of result volatility or how an unknown city_id is handled.

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 sentences, zero filler. The capability statement leads, the output promise follows, and the sibling diversion lands last where it is easiest to act on.

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 no output schema, the description carries the burden of telling the agent what comes back, and 'each pick says why it was chosen' does that at the right level of detail. Combined with 78% schema coverage and full annotations, an agent has what it needs to call this correctly.

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 78%, so most parameters are already documented inline, and the description mostly restates them in prose (interests, periods, headline vs hidden gems, indoor/outdoor, time available). It adds no syntax or behavioral detail beyond the schema, and never mentions limit, exclude_ids or language.

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?

Specific verb+resource (personalized attraction picks in one city) with the ranking inputs named: interests, historical periods, must-see vs hidden gems, indoor/outdoor, time budget. It also adds an output promise ('Each pick says why it was chosen') that separates it from a plain filtered search such as search_attractions.

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 routes the agent away with 'Use plan_walking_tour instead when the traveler wants an ordered route', giving both the alternative and the selecting condition. It leaves the search_attractions vs recommend_attractions boundary implicit rather than stated.

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