Compare prices for one hotel across booking sites (Booking.com, Hotels.com, Expedia, etc.).
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | Specific hotel name + city | |
| country | No | Country (default: us) | |
| check_in | No | Check-in YYYY-MM-DD | |
| currency | No | Currency (default: USD) | |
| check_out | No | Check-out YYYY-MM-DD |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
There are no annotations, so the description carries the full burden of behavioral disclosure. It clearly indicates this is a read-only comparison across booking sites and lists example sites. However, it does not disclose return format, whether it requires dates, or any caveats about data freshness or site coverage, which would be helpful for a complete behavioral profile.
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, front-loaded sentence that states the core action and scope with no redundant words. It earns its place by naming example booking sites and clarifying the single-hotel scope.
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 no output schema and no annotations, the description should explain expected return values and any prerequisites. It does not mention what the comparison output looks like, whether check-in/check-out are needed for accurate pricing, or how optional parameters affect behavior. The core purpose is clear, but the description is not fully complete for agent 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 input schema already provides 100% coverage with meaningful descriptions for all five parameters, so the baseline is 3. The description does not add parameter-level detail beyond what the schema provides, though it reinforces the 'one hotel' context for the query parameter.
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 uses a specific verb ('Compare') and identifies a clear resource ('prices for one hotel across booking sites'). It also distinguishes itself from sibling tools like cheapest_hotels by explicitly scoping to a single hotel, making the tool's purpose unambiguous.
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 phrase 'for one hotel across booking sites' clearly implies when to use this tool (when you have a specific hotel and want to compare prices across multiple sites). It does not explicitly name alternatives or exclusions, but the context is clear enough that an agent can differentiate it from sibling tools like cheapest_hotels or hotel_search.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool addresses a distinct aspect of hotel research: neighborhoods, cheapest options, server health, hotel details, price trends, general search, nearby attractions, and cross-site price comparison. There is no functional overlap between tools.
Tools follow a consistent snake_case convention with descriptive names. Most are noun_noun or adjective_noun patterns (area_guide, hotel_details), with only price_compare using a verb form. The pattern is clear and predictable, though not perfectly uniform.
Eight tools cover the full spectrum of hotel information retrieval without being excessive or sparse. Each tool serves a specific, necessary function for travelers researching accommodations.
The tool set provides end-to-end coverage for hotel research: searching, filtering by price, comparing across booking sites, viewing price calendars, checking nearby places, and getting detailed reviews. There are no obvious gaps for the intended information-only use case.