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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the description is not obligated to cover safety. It still adds real value beyond them: the exact field set returned, the deliberate omission of reviewer display names for privacy reasons, and the meaning of an empty result. It does not mention any result cap or truncation behavior for cities with many reviews, which is the one behavioral gap.

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?

Content is front-loaded: what is returned, then the required input, then the privacy caveat, then the routing alternatives. Nearly every clause earns its place, but "so do not expect an author field" restates the preceding clause about names not being returned, which is minor redundancy in an otherwise tight definition.

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 only two parameters, an output schema present, and read-only annotations, the description covers everything an agent needs: what it returns, the required input, the vertical options, the privacy-driven shape of the payload, and the valid empty-result case. Nothing material is left to inference.

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% across two parameters, so the baseline would be 3 even with nothing added. The description does add one genuinely useful clarification – that city_id is required – which the schema itself does not enforce (no required array), and restates that vertical accepts experiences (default) or attractions, though that duplicates the schema. The added meaning is real but thin.

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 opens with a specific verb and resource ("Return city-level Klook reviews") and enumerates the exact payload: review body, score, time, plus the reviewed activity's title and URL. It also scopes the inputs (city and vertical) so the agent can distinguish this from klook_search, klook_attractions_search and klook_activity.

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?

It states the routing conditions explicitly: use klook_search or klook_attractions_search to locate the reviewed activities, and klook_activity for a single activity's card, implying this tool should not be used for discovery. It also sets expectations for the degenerate case ("A city with no reviews returns an empty list, which is valid"), preventing an agent from treating an empty result as an error.

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