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

Annotations only declare the safe-read profile (readOnlyHint=true, openWorldHint=false, destructiveHint=false). The description adds substantial non-obvious behavior: it combines and deduplicates tickets, preserves route semantics, sorts globally by price when price sorting was used, and renders an explicit empty state.

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 action and its timing, then layered with the constraints and the rendering contract. Every sentence carries unique instructions (timing, pass-through, merge/dedup/sort behavior, do-not-recreate) with 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?

For a one-parameter, high-coverage schema with an output schema present, the description covers everything an agent needs: invocation timing, exact input expectations, merge semantics, and the UI presentation contract. Nothing material is left to inference.

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% and the schema says to pass results unchanged in search order, so the baseline would be 3. The description goes further by spelling out the consistency rules between the combined result set (same route, currency, market, locale, one-way, sorting, unique; differing dates/pages/limits/direct allowed), which the schema does not express.

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 ('Render one final Flaut.Travel route-price widget') and explicitly scopes it to the terminal step after search_route_prices calls. This unambiguously separates it from the sibling search_route_prices, which only retrieves data.

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 when-to-use ('exactly once, after all search_route_prices calls are complete') plus named alternatives to avoid ('do not recreate it as a separate card grid, list, or table'). It also lists which fields must match across searches and which may differ, so the agent knows exactly what input is acceptable.

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