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

Annotations already declare readOnlyHint=true, openWorldHint=true and destructiveHint=false, so the safety profile is covered. The description goes beyond that with genuinely useful behavioral context: prices are cached user-sourced data (not an offer), the 48-hour staleness window, and that empty tickets means no cached match rather than no flights. It does not disclose pagination limits or result caps, but the schema carries those.

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 is front-loaded in the first clause, then the sentences proceed in call order: data nature, locale rule, required inputs, date formats, batching, rendering, empty-result meaning, special modes, prerequisite. Dense but every sentence changes agent behavior, so nothing is wasted.

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 13 parameters, an output schema present, and annotations covering safety, the description supplies precisely the missing pieces an agent needs: date-format policy, minimum input rule, batching workflow, follow-up render call, and empty-result interpretation. Nothing required for a correct invocation is absent.

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 100%, so the baseline is 3. The description adds meaning the schema does not: 'Provide at least origin or destination' as a cross-field rule, the origin+unique=true combination for cheapest-destination discovery, and the constraint to reuse the same market and trip settings across periods. It does not clarify sorting/currency/page interactions, so it is not a 5.

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?

Names a specific verb+resource ('search for cached route prices') and immediately scopes it as 'data-only', which cleanly separates it from the rendering sibling render_route_prices. The 'from the monolith backend' qualifier plus the cached/48-hour framing tells the agent exactly what kind of data it will get.

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 explicit conditional rules: YYYY-MM for months/seasons/flexible dates, YYYY-MM-DD only when the user named an exact day, never invent a day. It names the pre-requisite sibling (resolve_city_iata_code), the follow-up sibling (render_route_prices exactly once), and the multi-period calling pattern with same market/trip settings. This is when-to-use guidance at its most actionable.

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