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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), so the bar is lower. The description adds stateful behavior beyond that: it consumes an outbound itinerary_id, returns complete itineraries with the trip total, and flips 'needs_leg' to false once the trip is whole, which tells the agent about the tool's role in a multi-step flow.

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 tight sentences with zero padding. The most important fact (when to call it, and after what) is front-loaded, and each subsequent sentence adds a distinct piece of context.

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 an 11-param tool with full schema coverage and an output schema, the description covers sequencing, prerequisites, scope of filters, and the multi-leg flow. Nothing an agent needs to invoke it correctly is missing, and the return-shape mention is a harmless reinforcement of the output schema.

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 baseline is 3. The description adds value beyond the schema by clarifying filter scope ('Filters apply to the leg being chosen') and characterizing itinerary_id as an outbound or partial multi-city id, which the schema states only generically.

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?

The description states a specific verb and resource ('search return flights') and anchors it to a sibling: 'Use after search_flights'. It distinguishes the tool from the plain flight search by its role as the second leg, so an agent can tell them apart without opening either schema.

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?

It gives explicit sequencing ('Use after search_flights'), conditions for use ('when the traveler wants a specific return, or the next leg of a multi-city trip'), a repetition rule ('once per remaining leg'), and an exclusion ('Not needed for an outbound watch'). When-not guidance is present alongside the when.

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