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

Annotations already mark this read-only/idempotent/non-destructive, but the description adds substantial behavior beyond them: result cap (up to 20), that empty fields mean unknown rather than bad, that shortlist_url is a shareable comparison page, that catalogue vs non-catalogue cities use different backends, and that sample_estimate is a previously observed price rather than a quote. It also states the privacy constraint 'Never send names, email addresses or payment details'.

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 usage rule is front-loaded, and most sentences carry distinct, non-redundant information (return shape, backend differences, sample_estimate caveat, privacy rule). It is dense and long, however, and runs several topics together without clear segmentation, which slightly reduces scannability.

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 an 11-parameter open-world search with no output schema, the description explains the key returned fields (area, station, amenities, price, score, sample_estimate, shortlist_url) and the two backend behaviors, which is strong. It stops short of covering a few filters (min_rating, max_price_per_night, country_code, stars), leaving those to inference.

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?

With only 18% schema coverage, the description carries much of the semantic burden: it clarifies that query words match amenities, that dates must be supplied together or not at all, the occupancy limits (1-8 adults, up to 6 children, one room), and the limit cap of 20. It does not explain min_rating, stars, max_price_per_night or country_code semantics, so it compensates partially rather than fully.

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 gives a specific verb+resource ('Find hotels by city, name or preferences') and clearly frames the tool as recommendations/comparison. It distinguishes itself from siblings by routing the traveler's link to get_booking_link and implying get_hotel handles a single hotel. An agent can identify the tool's role without opening the 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?

It explicitly states when to use it ('when the user wants hotel recommendations or wants hotels compared') and names the alternative for a different need ('Use get_booking_link for the traveler's link'). It also gives the precondition 'Supply both dates or neither', but offers no explicit when-not guidance, keeping it 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.