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

With no annotations, the description carries the full burden and does so: it discloses that the tool calls a metered supplier (cost implication), that booking links go stale in minutes, and that a link is not a reservation and neither the tool nor the agent can hold a room. It also supplies output-expectation guidance (never claim a stay is booked, held or confirmed), which is exactly the behavioral context that annotations would otherwise 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 purpose and cost warning are front-loaded, and every sentence carries operational weight. There is minor redundancy: 'A LINK IS NOT A BOOKING' and 'This tool cannot reserve a room' restate the same constraint in adjacent sentences, which a tighter edit could merge.

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, the description still conveys what comes back (rooms, prices, per-room booking links), their volatility, and the hard boundary on what the tool cannot do. For a 4-parameter metered call, nothing an agent needs to invoke or report it correctly is missing.

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%, so slug, adults, checkin and checkout are already documented in the schema, making 3 the baseline. The description only gestures at the shape ('one hotel and a stay window') and adds no format or semantic detail beyond that.

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?

States a specific verb+resource: live rooms and prices for one hotel within a stay window, plus a booking link per room. It also positions itself against siblings by naming get_evidence as the decision tool and framing itself as the closing step, so an agent can distinguish it from search_hotels and get_evidence without opening a schema.

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?

Explicit when/when-not with a named alternative: use when a traveler has settled on a hotel and wants to book, never to browse or compare several, and 'Decide with get_evidence first.' The conditional routing is fully specified rather than left to inference.

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