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

Annotations only supply readOnlyHint=true and openWorldHint=false, but the description adds real behavioral context: the index is computed from Fantasize's own nightly pricing of every sailing and each sailing is compared only with its own earlier price, so new sailings and sell-outs never distort it. It also discloses that press releases are bundled into the return payload. No rate limits or pagination behavior are mentioned, keeping it out of 5 territory.

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?

Three sentences, front-loaded with the definition, then the return shape, then the drill-down instruction. The middle sentence is long and stacks five breakdown dimensions, but every clause carries information the agent needs.

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 no output schema and only three optional parameters, the description carries the burden of describing returns and does so thoroughly: overall level and change, the same broken out by company (with ticker), line, region and months to departure, plus press releases. Nothing needed to call this tool correctly is missing.

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 already 100%, so the baseline is 3, but the description adds meaning the schema does not: group values map onto the breakdown categories (company, region, lead time) with examples like "Royal Caribbean Group", "Alaska", "3-6 months out", and it notes that the company cut carries a stock ticker. It does not add anything about 'days' or 'cut' beyond 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?

The description gives a specific verb-adjacent purpose: an index of how the price of the same cruises moves night to night, plus what it returns (overall level and change, plus breakdowns). It is unmistakably an aggregate trend tool rather than a single-cruise lookup, which implicitly separates it from check_price and search_cruises. It never names a sibling explicitly, so it stops short of a 5.

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?

The title frames the use case (are cruise prices rising or falling?) and the last sentence tells the agent how to drill down: name a group to get its daily series. There are no explicit when-not conditions or named alternatives, 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.