search_hotels

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

With no annotations, the description must carry the full behavioral burden, and it does well. It discloses that results are grouped by category, includes cancellation/deposit terms, that no winner is auto-selected (non-committal), that government scope defaults to federal-only, and that adults/children are per room. It does not cover pagination or result limits, but those are partially encoded in parameters. Overall, it adds substantial behavioral context beyond the 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 a single dense paragraph with no wasted words. Each sentence adds value: the main purpose, the grouping and terms, the government default, the note about unknown categories, the no-winner caveat, and the per-room clarification. It is front-loaded with the core function and keeps clarifications brief. Not overly long for the complexity of the 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?

There is no output schema, so the description must describe return values, and it does: 'return all matching offers, grouped by category, with cancellation/deposit terms and eligibility.' It also covers key behavioral nuances like the default scope and the no-selection policy. It could add details on pagination (maxPages/maxResults) or error handling, but given the 12 parameters and the absence of an output schema, it is largely 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?

Schema description coverage is only 33% (4 of 12 parameters have descriptions). The description compensates by explaining key parameters: specialRates is 'searched separately' and returns all offers; governmentScope has a default and filtering logic; rateType is deprecated; adults/children are per room. This adds meaning that the schema lacks, especially for adults/children semantics and the specialRates search behavior.

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 clearly states the action: 'Search each selected specialRates category ... and return all matching offers, grouped by category, with cancellation/deposit terms and eligibility.' It names the resource (hotels, implied by tool name and destination parameter) and provides a specific verb. It also differentiates from siblings by explicitly stating 'No winner is selected' and referencing select_room/checkout, which clarifies its role in the workflow.

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 gives concrete usage context: 'present the options to the user before select_room or checkout' tells when to use this tool versus the selection/checkout steps. It also clarifies defaults (government scope federal-only) and edge cases ('Unknown categories are not sold out'). However, it does not explicitly mention alternatives or when not to use it beyond the workflow sequence, which is slightly less explicit than ideal.

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