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

With no annotations, the description carries the full burden and does well: it discloses case-insensitivity across filters, substring matching for title, OR-within-filter / AND-across-filter logic, inclusive range formats, the default sort ordering, and that each row's price stays in its own currency. It stops short of describing the returned row shape or any rate/auth constraints, but for a read-only search this is substantial.

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?

Dense but front-loaded: the purpose sentence comes first, then filter semantics, then sort behavior and defaults. Nearly every sentence carries operational information, though the sort-field enumeration is list-heavy and could be tightened.

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 12-parameter, zero-required search tool with no annotations and no output schema, the description covers filtering, combination logic, ranges, sort syntax and defaults well enough to call correctly. The main remaining gap is what a returned row looks like beyond the per-currency price note, which is not covered anywhere else.

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 the baseline is 3, but the description adds real meaning beyond the schema: cross-parameter OR/AND combination rules, the exact accepted range syntax for nights/price/ppd and departs, and the sort field alias mappings (cruiseline=line, source_label=source, number_of_days=nights, lowest_price=price, price_per_day=ppd, comment=rate). The nested anyOf array/string acceptance for line/source/ship is left to the schema.

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: 'Search the latest published cruise fares', with scope clarified as 'the full crawl, including Contitrans and Crusit'. It references describe_rates as the source of valid line/source/ship values, which gives partial sibling differentiation, but never states plainly what search_rates does that describe_rates does not.

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 implied through the filter semantics ('Empty line, source, ship, or rate means all of that dimension') and the pointer that those values 'must otherwise match describe_rates', which hints that describe_rates enumerates valid values. However, there is no explicit when-to-use/when-not statement telling the agent to call describe_rates first or in place of this tool.

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