find_reviewed_hotelsFind hotels that have editorial reviews. Filter by city and minimum overall grade; optionally rank by one category (location, rooms, service, dining, facilities, value).
| Name | Required | Description | Default |
|---|---|---|---|
| city | No | Only hotels in this city, e.g. 'Istanbul' | |
| limit | No | Max results to return (default 10) | |
| category | No | Rank results by this category's grade | |
| min_grade | No | Minimum overall grade, e.g. 'B+' |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavioral traits. It implies read-only behavior but does not explicitly state that no data is mutated, whether results are paginated (the limit parameter suggests it but behavior isn't described), what happens if no matching hotels exist, or if the ranking by category changes the result list order. For a search tool without annotations, this gap is notable.
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 sentence that front-loads the core purpose ('Find hotels that have editorial reviews') followed by concise details about filtering and ranking. Every word earns its place, with no redundancy or extraneous information.
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?
For a search tool with 4 parameters, no output schema, and no annotations, the description provides the essential purpose and parameter usage but lacks completeness in behavioral aspects (e.g., pagination, edge cases, or return format). It is adequate for basic invocation but misses details that would help an agent handle complex queries or errors.
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 100%, and the input schema already documents each parameter clearly (city, limit, category, min_grade). The description adds aggregate context that all parameters are for filtering and optional ranking, but does not provide additional meaning beyond what the schema states. Baseline 3 is appropriate.
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 ('Find') and resource ('hotels that have editorial reviews'), and clearly distinguishes its scope (only reviewed hotels, filtering by city and grade, optional ranking by category) from sibling tools like get_hotel_review (which likely returns a single review) and list_cities (which lists cities).
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 specifies when to use this tool: 'Find hotels that have editorial reviews' with explicit filtering parameters (city, minimum grade) and optional ranking. It does not explicitly state when not to use it or mention alternatives among the sibling list, but the context is clear enough for an agent to infer usage scenarios.
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: booking advice, calendar events, last-minute deals, and city listing. No functional overlap.
All tool names follow a consistent verb_noun snake_case pattern (get_*, list_*), making them predictable.
With 4 tools, the server is compact yet covers the core functionalities of a hotel booking-timing service.
The tool set provides all necessary operations for the declared domain: advice, calendar, deals, and city discovery. No obvious gaps.