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

Adds substantial context beyond annotations: classification (publishes externally), durability, mutation modes, and a partial-failure policy of completed_items_not_rolled_back — that last point is genuinely valuable since destructiveHint=false might otherwise mislead. Also explains idempotency key derivation and the multi-seat authorization requirement for writes. Missing only success/failure semantics and required permissions.

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 operational metadata (classification, execution, mutation modes, failure policy) is front-loaded and useful, but a large middle block is generic response-formatting boilerplate about assistantSummary and never displaying raw JSON — that applies to every tool and doesn't belong in this definition. About half the text is non-tool-specific.

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 21-parameter, externally-publishing mutation with nested objects and an output schema, the description is too thin on the actual operation. It never states what trafficking creates or changes, prerequisites (e.g., creative must be approved, flight must exist), or the meaning of dryRun/force/approvalId. Output schema and annotations cover return shape and safety hints, but the core semantics are 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 0%, so the description carries the burden. It clarifies idempotencyKey derivation and seatId/seatName requirements on writes, which is helpful. But it says nothing about the 18 other parameters — accountId, flightId, creativeId (the required trio), targetMarket(s), locale fields, force, dryRun, approvalId, marketContext — leaving the agent to guess at their meaning and relationships.

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 opens with 'traffick creative', which is essentially a restatement of the tool name. It never explains what trafficking a creative actually does (e.g., associates a creative with a flight/campaign for delivery). The agent must infer intent from siblings like traffick_flight and retraffick_creative.

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?

No explicit statement of when to use this versus preview_trafficking_output, traffick_flight, or retraffick_creative. Mutation modes (validate_only, preview_only, execute) hint at a preview capability but don't clarify when to choose each or how they relate to dryRun/force.

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