search_hotels

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

With no annotations provided, the description carries full responsibility. It discloses that the tool does not perform currency conversion and only returns quotes as provided by the provider, which is valuable behavioral insight. It also warns against inventing currency codes, addressing a potential misuse. It does not mention response format or pagination, but the critical behavioral notes are present.

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 compact and front-loaded with the most critical information: 'Hotel search' first, then the currency requirement. Every sentence provides new information; there is no repetition or filler. It uses paragraphs effectively to separate key constraints from detailed behavior.

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 11 parameters, 3 required, 0% schema coverage, and no output schema, the description is quite complete for the core use case. It highlights the most critical constraint (currency) and warns against common errors. It does not explain each parameter or the return format, but the focus on the critical distinction from flight search is sufficient for an agent to call it correctly in most scenarios.

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 0%, so the description must clarify parameter meaning. The description emphasizes that 'currency' is required despite the schema listing it as optional (default null), which is a critical clarification. It also implicitly clarifies that 'location' is a hotel destination, not an airport. However, many parameters like 'top', 'rooms', 'adults' remain unexplained, but the essential parameter (currency) is well addressed.

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 begins with 'Hotel search', a specific verb-resource pair that clearly distinguishes it from sibling tools like search_flights or search_trip. It further defines the scope by specifying currency requirements and its distinction from flight-related searches, making it immediately recognizable.

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?

The description explicitly states that currency is required and clarifies that no origin airport is involved, which helps distinguish from flight search tools. It does not explicitly name alternatives, but the key constraint (currency required, no origin) is clear enough to prevent misuse. There is no explicit 'when not to use' guidance, but the emphasis on currency and the absence of origin implies the tool is for hotel-only searches.

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