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

Annotations already declare readOnly/openWorld/non-destructive, and the description adds genuinely new behavioral facts: a hard cap of 5 results, no pagination, indicative figures, and that the product page overrides the returned price/cover. Those caveats materially change how an agent should present results. It stops short of saying whether an empty or filtered-out result set is a normal outcome.

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 short sentences, front-loaded with the return shape and result cap, followed by the two caveats that matter (no next page, indicative figures). Every sentence carries distinct information with no restatement of the name or title.

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 19-parameter, nested-object tool with an output schema present, the description covers what matters an agent cannot get from structured fields: result count ceiling, absence of pagination, and data authority. Return-value detail is legitimately delegated to the output schema. Only minor gap is no explicit hand-off to get_travel_plan for full plan detail.

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 carries the parameter semantics and baseline 3 applies. The description adds only indirect value — mentioning the three comparison axes and the 5-result cap, which hints that the many boolean and premium filters are narrowing conditions. It does not explain interaction between filters or defaults beyond what the schema states.

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 ('Return at most 5 single-trip travel plans') plus the dimensions being compared (destination, trip length, traveller mix) and the fields returned. It is clearly a ranked list/comparison operation, though it never names the sibling get_travel_plan as the way to drill into one plan, so differentiation from siblings is inferred rather than stated.

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 by constraints ('Must be single. Annual travel is rejected.', 'There is no next page') and by priorRecommendationId being scoped to 'when this call continues that comparison'. There is no explicit statement of when to call this versus get_travel_plan or describe_travel_decoder, aside from an incidental pointer that regionCodes come from describe_travel_decoder.

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