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

Annotations already cover safety (readOnlyHint=false, destructiveHint=false, idempotentHint=true), but the description adds genuinely useful behavior: durable execution, a partial-failure policy of 'completed_items_not_rolled_back', deterministic idempotency-key derivation on omitted keys, and the hard requirement that seatId/seatName be supplied on the exact write call. It omits concurrency behavior around expectedVersion, which is a notable gap for a write tool.

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-loads mutation classification and execution semantics, which is good, but the first sentence is pure tautology and the block of assistantSummary/raw-JSON display rules reads as reusable boilerplate rather than tool-specific guidance. It is not bloated to the point of harm, but several sentences would apply equally to any tool in this server.

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?

An output schema exists so return values need no explanation, and the description does cover the write-guardrails an agent must respect before calling. Given 14 parameters, nested creative config arrays, and 0% schema coverage, however, the parameter side is substantially under-specified for a tool of this complexity.

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% across 14 parameters, and the description only explains two of them (idempotencyKey derivation and seatId/seatName). Nothing is said about flightId, name, expectedVersion, dryRun, or the creatives/thirdPartyTags payloads, so the definition leaves most parameters undocumented in both places.

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 opening 'update flight' essentially restates the tool name, and the description never says what about a flight can be updated or what the scope of the write is. The classification line ('writes to Studio') and mutation modes vaguely imply a mutating flight operation, but nothing distinguishes it from validate_flight, create_flight, or traffick_flight, all of which appear as siblings.

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?

Mutation modes (validate_only, preview_only, execute) and the seat-authorisation rule imply when the tool is appropriate, and the seat rule is a concrete precondition. However, there is no explicit direction on when to choose update_flight over validate_flight or delete_flight, and no stated exclusions.

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