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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantially more: a 1,000 cap, newest-first ordering, the 24-month window, the bad-review threshold (score of 4 or less out of 10), absence of reviewer names, and the meaning of available=false. It also discloses the output contract (staylist_page, booking_links) and the counting semantics the agent must preserve.

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 purpose and scope, then behavior, then output contract - every clause carries information. The downside is that it is one dense run-on paragraph mixing retrieval facts, output shape, and editorial instructions (quote faithfully, report the denominator), which makes it harder to scan than a structured form would be.

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?

There is no output schema, so the description carries the return-value burden and does so: review counts, bad-review texts, staylist_page, booking_links, and nearby_with_reviews when available=false. Combined with the annotations, an agent has everything needed to call it and interpret the result.

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 coverage is 100%, so both parameters are already documented; the description still adds meaning by defining 'bad' numerically (1–2 star / score of 4 or less out of 10) and clarifying that only_bad=false returns the most recent reviews of any score. The hotel_id linkage to search_hotels is only in the schema, not 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?

Specific verb+resource ('Guest reviews for one hotel') with explicit scope: last 24 months, up to 1,000, newest first, sourced via LiteAPI. It also names its companions (get_booking_link, search_hotels for the id), so the agent can place it among siblings 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?

Usage is clearly framed ('so the traveler can see what went wrong... before booking'), the default of only_bad=true is stated with the with-only_bad=false alternative spelled out, and the available=false path routes to nearby_with_reviews. It lacks an explicit statement of when NOT to call this versus a sibling (e.g., when no hotel_id is known yet), so it stops 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.