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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the description doesn't need to restate those. It adds value by listing what fields are compared (e.g., price verdict against six-month average, CDC inspection score), giving the agent a concrete picture of the output. It doesn't disclose any side effects or error conditions, but those are covered by the read-only annotation and are not expected.

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 description is a single sentence that front-loads the core action and then lists the comparison fields efficiently. There is no filler or repetition, and every clause adds information about what the tool does.

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?

The description lists all the comparison dimensions, which is what an agent needs to know about the output. It also mentions the prerequisite (ids from searchCruises). Since there is no output schema, this description serves as the primary source for expected results. It could mention constraints like max 3 sailings, but that's in the schema. Overall, it's complete for an agent to decide when and how to use it.

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 50% per signal, though both parameters actually have descriptions in the schema. The description only mentions the source of ids ('from searchCruises') and does not elaborate on the cabin parameter at all. The schema already explains cabin types and ids format, so the description adds minimal semantic value beyond what the schema provides. At 50% coverage, the description should compensate more but doesn't.

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 states a specific verb ('compare') and resource ('sailings'), scoped to '2–3 specific sailings', and enumerates the exact comparison dimensions (dates, ports, price, verdict, ship age/size, family suitability, rating, CDC score). This clearly differentiates it from siblings like searchCruises (which finds sailings) and getPriceHistory (which shows trends).

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 description explicitly says 'Takes sailing ids from searchCruises,' which establishes the prerequisite workflow: first search, then compare. It implies the tool is for comparing already-selected sailings rather than discovery. It doesn't explicitly name alternatives or when not to use it, but the reference to searchCruises gives clear usage context.

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