hotels_reviews

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

No annotations are provided, so the description bears the full behavioral burden. It does nicely disclose that the output is bounded ('a bounded set of highlighted guest reviews') and that the archive is not exposed, which is a significant data-return limitation. It also states the rating scale (0-10) and the review fields. Missing auth, rate limits, or pagination details are less critical for a read-only tool, and the main behavioral constraints are well described.

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?

The description is a single block of four sentences, each earning its place: the first defines purpose and output, the second covers the exact return payload fields, the third explains the parameter provenance, and the fourth states the missing piece (archive). No fluff, no tautology; the text is front-loaded and stays on point.

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?

Given there is no output schema and no annotations, the description compensates well by listing the return data categories, rating scale, highlighted-review fields, verified-stay flag, and caveat about pagination. The only gap is the exact JSON payload for the 'request' parameter; but since the description identifies the key field (property_id) and its source, an agent can likely construct a correct call. This is near-complete.

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?

The input schema has only one parameter, 'request', with a generic 'Reviews request' description, and schema description coverage is 100%. The description adds meaningful guidance for sourcing property_id as a numeric global id from Search response's properties[].id, which the schema alone doesn't provide. It does not, however, explicitly lay out the internal shape of the request object (e.g., {request: {property_id: ...}}), so the agent must infer that from the word 'property_id'.

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 states a specific verb-resource pair ('Get Hotels.com guest reviews') and meticulously specifies the returned fields: overall rating with label, per-category sub-ratings, and highlighted reviews with reviewer/date/rating/text/verified-stay flag. It also differentiates from hotels_reviews_archive by explicitly noting the full paginated archive is not exposed, so an agent can immediately tell which tool to pick.

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 explains that the tool targets one property's review overview and that property_id must be taken from a Search response's properties[].id, anchoring it in a concrete workflow. It implicitly tells agents not to use it when they need the full paginated archive (a sibling tool obviously exists), and while it doesn't name the sibling, the exclusion is clear. Slightly more explicit alternative routing would make it a 5.

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