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

Annotations already declare readOnly/idempotent/no-destructive, and the description adds genuinely non-obvious behavior: supplied options layer on top of search selections, omitted options inherit search values, and prior-call options are NOT remembered so every changed option must be resent. It also explains that 'detail' modes shape response size ('full' adds every photo, 'policies' keeps policies concise). This is exactly the statefulness/overwrite context annotations cannot convey.

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?

Front-loaded with the primary purpose, then usage constraints, then behavioral caveats, ending with a concrete example — a sensible ordering with little waste. The prose is dense and a couple of clauses (e.g. the photo/policies detail note) could be tightened, but every sentence carries 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?

An output schema exists, so return values need not be described, and the description covers the statelessness caveat, detail-level tradeoffs, and the book-vs-read boundary that matter for correct invocation. Gaps remain around 'market' and 'response_format', which an agent must infer from the enum/default alone.

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 0%, so the description must carry the load, and it partially does: it explains the options merge/inheritance rule and the semantics of the 'detail' enum values, which are the most error-prone inputs. However, 'market', 'response_format', and the identity params 'search_id'/'offer_ref' get no explanation beyond a bare example, and the ~18 nested option fields are undocumented in the description.

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 and resource ('read current pricing, deposit, extras and rental policies') and anchors it to the sibling it follows ('after search_offers'). An agent can distinguish this from search_offers and the reservation tools without opening any 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 precondition ('Use after search_offers') plus an explicit exclusion ('Do not use to book or confirm a reservation'), with booking siblings clearly the alternative for that intent. Nothing is left to inference about when to select this tool.

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