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

Annotations only declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=false; the description adds substantial behavioral context beyond them — no reservation or hold is created, nothing is sent to the host, the returned link expires after 24 hours, anyone else may book the nights in the meantime, and there is a per-caller rate limit. This is exactly the disclosure an agent needs for a non-idempotent, non-holding link-generation call, and it contradicts nothing in the annotations.

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 front-loaded with the core action and return value, and the negative guarantees are stated up front where they matter. It is slightly redundant in places ('reserves NOTHING and books nothing: no nights are held, the host is not told, no e-mail is sent'), but that emphasis is defensible for a tool whose failure mode is an agent falsely telling a guest they are booked.

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 nine-parameter tool with a nested guest object and no output schema, the description covers what is returned (checkoutUrl), who must act on it (the guest), its expiry (24 hours), the booking race condition, and rate limits. Nothing critical for correct invocation 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 the schema already documents all nine parameters, including that guest/contact details and message are optional and pre-fill the form. The description restates this ('contact details are optional and only pre-fill the form, which the guest can change') but adds no syntax, format, or constraint detail beyond what the structured schema provides, so the baseline of 3 applies.

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 states a specific verb and outcome — preparing a stay for the guest to confirm and pay, returning a checkoutUrl — and immediately bounds the scope with what it does NOT do (reserves nothing, books nothing, no email). It also distinguishes itself from the siblings by naming the required prerequisite step ('Quote first', i.e. get_quote), so an agent can place it in the workflow without opening schemas.

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 clear sequencing guidance ('Quote first') and explicit when-not-to-act instructions ('Never tell the guest they are booked, and never try to complete the booking for them'), plus a rate limit. It does not explicitly name the alternative sibling tools by name, which keeps it just short of a 5.

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