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

The description discloses much beyond the annotations: 'Execution: durable', 'Partial failure policy: completed_items_not_rolled_back', idempotency derivation when idempotencyKey is omitted, and the seat requirement. It also explains the return value is internal application state and gives response-formatting instructions. No contradiction with annotations (readOnlyHint=false, idempotentHint=true).

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?

The description is a dense, single-paragraph block containing valuable information but also generic response-style instructions. It is front-loaded with the core classification but could be more scannable with bullet points or sections. Some sentences (e.g., about assistantSummary and never showing raw JSON) feel like boilerplate rather than tool-specific content.

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 complex mutation with 13 parameters, no schema description coverage, and no explanations of core inputs, the description is incomplete. It covers operational traits like durability and partial failure, but omits domain semantics such as what a flight is, which fields are updatable, and prerequisites (e.g., whether the flight must exist or be in a certain status).

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 0%, and the description does not compensate for the 13 parameters. It explains idempotencyKey and seatId/seatName requirements, but fails to describe the meaning of core parameters like flightId, creativeConfigs, expectedVersion, dryRun, or accountId. The agent is left without semantic guidance for most fields.

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 clearly states 'update flight' with 'Classification: writes to Studio', establishing a specific verb and resource. It distinguishes itself from siblings like get_flight (read), validate_flight (validation-only), and delete_flight (destructive) by framing this as the write/update tool.

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?

The description includes mutation modes (validate_only, preview_only, execute), which guide when to use this tool versus a pure validation tool. It also provides important usage conditions: seatId/seatName must be supplied on the exact call when multiple seats are authorized, and idempotencyKey behavior. However, it does not explicitly name alternatives such as validate_flight or create_flight.

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