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

With no annotations, the description discloses the return shape ('returns excerpts; ok:false means no answer'), instructs the agent to admit lack of knowledge and offer a human, and clarifies that a service request should be answered with facts rather than by placing an order. This goes well beyond what the name or schema alone would provide.

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: scope and purpose come first, followed by usage, output, and failure handling. Every clause carries information, with no repetition of the tool name or schema boilerplate.

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 read-oriented info tool with no output schema, the description is complete: it covers input scope, return behavior, the ok:false failure case, and the prescribed agent response. It also provides enough context against the sibling list to prevent misuse for availability/pricing.

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 documents all three parameters at 100% coverage. The description adds query-level guidance about which topics and service requests are valid inputs, and reinforces the boundary between hotel facts and availability/pricing, so it adds modest value beyond the schema.

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 first sentence names a concrete operation: returning guest-facing hotel knowledge-base facts, and enumerates the content domains (check-in/out, breakfast, parking, rules, services, directions). It explicitly excludes availability and pricing, which distinguishes it from siblings like get_hotel_availability and quote_stay.

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 an explicit positive trigger ('call for any hotel question except availability and price, and for service requests') and says how to handle a service request without executing it. It does not name the sibling tools that cover the excluded cases, so cross-tool routing is clear but slightly implicit.

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