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

Beyond the readOnly and idempotent annotations, the description discloses important behavior: items without a price are real hotels with no published rate and must not be called unavailable; price_from_eur_per_night is only a starting price; the URL is the only way to book/buy. This adds substantial context beyond the annotations and schema.

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 dense but every sentence carries useful operational guidance: price display formatting, no-price handling, and URL requirements. It is a single large paragraph and the opening catalogue/geography sentence is somewhat broad, but it remains focused enough for a 17-parameter tool.

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 that an output schema exists, the description appropriately does not need to re-explain return shapes, yet it still covers key output semantics and the no-price edge case. It does not mention partial-hotel-name search via query or explicitly require one of city/lat/lng, but the schema covers those details, so the description is sufficient for normal invocation.

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 description adds meaning not in the schema: city can be English or local, country disambiguates, lat/lng should be combined with radius_km, and adults/check_in/check_out should be passed so URLs open with dates. Some parameters without schema descriptions, such as page, sort, and stars_min, receive no elaboration, so it is not fully exhaustive.

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 and resource: 'Search hotels on HotelsCasa' and clarifies the catalogue scope, search modes, and item fields. It does not explicitly contrast with search_properties or other search siblings, so sibling differentiation is left partly to inference, though the hotel-specific fields make the purpose clear.

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 gives clear context for when to use city vs. lat/lng, when to add country to disambiguate, and that country alone returns its main cities. It also instructs to pass check_in/check_out/adults so links open with dates, but it does not name alternative tools or say when not to use this tool.

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