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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's job is to add operational context — and it does: coverage is limited to captured sailings from 14 named lines, returns are sailing links, prices are USD cents per person for two guests and are not live or family quotes, and the default is three results. The only gap is that return shape and pagination behavior are left to the output schema.

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?

Purpose and coverage are front-loaded correctly, but the back half degrades into telegraphic fragments ("Research only; no widget. Default three choices.") whose referents are unclear. Information density is high, yet the sentences are not ordered by what an agent needs first — the term-ID and suggestion workflow arguably belongs earlier alongside the purpose statement.

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 25-parameter search tool with an output schema and full read-only annotations, this covers the essentials: data coverage boundaries, price semantics, caveats about live inventory, and a required companion tool for resolving names. Defaults for view/pageSize are stated. Only minor gaps remain, such as sort defaults and how the groups view interacts with paging.

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 88%, so the schema already documents nearly every parameter and the description can only add on top. It contributes two useful behavioral notes — the price unit (cents per person, two guests, not a party total) and the instruction not to invent cabin/budget constraints — plus the "filter before grouping and choosing lowest cabin price" ordering hint. These are genuinely additive but thin given 25 parameters.

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?

Opens with a specific verb+resource ("Find cruise recommendations and deals on CruiseHops") and enumerates the filterable dimensions (destination, departure port, dates, cabin, budget). It clearly scopes the data set with the notable caveat "not a whole-market or live-inventory search." It stops short of distinguishing itself from siblings like compare_sailings or present_cruises, which an agent must still infer from names alone.

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?

Gives concrete usage rules: "Use term IDs from suggest_cruise_terms for precise names," "Do not add cabin or budget constraints the user did not give," and the note that this is research-only with no widget. It also sets expectations about coverage limits. What it lacks is explicit routing — it never says when to prefer compare_sailings or present_cruises instead.

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