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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), yet the description adds genuinely new behavior: rendering is done by the host not the agent, invalid/expired ids are silently dropped and named in the result, and there is a strict once-per-answer invocation constraint.

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?

Front-loaded with the core action, then the invocation rules, then the failure mode. Every sentence carries operational information; no filler.

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, the description still tells the agent what the result contains (rendered cards) and what happens on bad input (id omitted and named in the result). An agent has everything needed to call it correctly and interpret the outcome.

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 handle, language, and cruise_ids. The description restates the cruise_ids constraint (3-5, recommended order) but adds nothing about the handle or language parameters, so it only meets the baseline.

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+resource ('Shows the user the cruises you are recommending') plus the rendered form (cards with ship photo, route, dates, price, booking link), and explicitly negates the sibling behavior ('It does NOT search'), separating it cleanly from find_cruises.

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?

Highly explicit: call ONCE, as the LAST step, with 3-5 cruise_id values from a previous find_cruises result in recommended order; never before deciding, never more than once per answer. It also names the recovery path (call find_cruises again) when ids are unknown or expired.

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