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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds substantial behavior beyond that: amenities are ranking preferences while required_amenities are hard filters, exclude_offer_ids suppresses already-seen offers, and price is only returned when dates and party are supplied. It also discloses the non-obvious fallback: with dates, if fewer than 3 offers exist in the town, nearby localities are added and flagged via a `nearby` field with distance.

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 paragraph is front-loaded with what the tool searches and its filter axes, followed by return content, ranking semantics, pagination, and the nearby fallback. It is dense but each sentence earns its place, though the single block runs long and could be broken into clearer clauses for a 16-parameter tool.

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?

With an output schema present, the description need not detail return shape, yet it still summarizes offer fields (summary line, rating, availability, total price, link). Combined with full parameter coverage and annotations covering safety, it discloses the ranking, pagination, and nearby-fallback behaviors an agent needs to call and interpret results correctly.

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 16 parameters, and the description largely repeats these definitions (amenities as preference, required_amenities as hard requirement, exclude_offer_ids for seen offers). The only added nuance is that total stay price depends on dates and party, which is a return-value rather than parameter detail. Baseline 3 applies since the schema carries the semantic load.

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 opens with a specific verb and resource ('Searches accommodation offers on noclegowo.pl') and enumerates the filter dimensions (location, dates, party, amenities, budget, free text), which is far beyond a tautology. It clearly separates this discovery search from check_availability and get_offer_details by scope. However, it does not acknowledge the near-identically named sibling 'searchAccommodations', so tool selection between those two is left to inference.

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 operating context: 'Every request carries the full set of criteria' implies stateless full-context invocation, and the exclude_offer_ids note explains the pagination loop for retrieving further results. It stops short of naming alternatives (check_availability, get_offer_details) or stating when NOT to use this search, so it is clear context without exclusions.

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