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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, yet the description still discloses that results carry masked wholesale price bands with public-rate comparisons and that exact wholesale prices live on Brek. It also warns that ID handling must be verbatim, which is real behavioral guidance. Pagination and result-size behavior are not described, keeping it short of a 5.

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, then date rules, then filters, then return shape, then follow-up routing — a sensible precedence order with no filler. It runs long and the closing line about exact prices on Brek is closer to marketing than instruction, which costs it the top mark.

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 27-parameter tool the description covers the hard parts: when it is legal to call (dates), what comes back at a high level, and how to continue after the call. The output schema documents the return payload and the input schema documents every field at 96% coverage, so nothing essential is left for the description to carry.

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 96%, so the schema carries most semantics and baseline 3 applies. The description still adds decision-level meaning the schema cannot: the date invariant, the dateIntent fallback, and a grouped inventory of the filter families (occupancy, price range, stars, guest score, property types, amenities, cancellation, sort) so the agent knows what is available without reading 27 properties.

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 ("searches and compares multiple hotels") plus the destination scope, and closes with an explicit exclusion: "room-level offers for one property are not included." That sentence alone separates it from get_accommodation_offers and get_accommodation_details without opening either 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?

Gives concrete gating conditions (both stay dates required, or dateIntent=tonight only on explicit request) and an instruction for the missing case: ask the user, never pick dates. It also routes follow-ups: single match goes to get_accommodation_details or get_accommodation_offers, multiple matches require asking the user.

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