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

The description significantly adds beyond annotations by disclosing 'writes to Studio, publishes externally', synchronous execution, partial failure policy ('completed_items_not_rolled_back'), idempotency key derivation behavior, and seat authorization requirements for mutations. These are critical operational details not conveyed by the annotations alone.

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 single dense paragraph that mixes purpose, execution metadata, response guidelines, idempotency, and seat rules. It is front-loaded with purpose but becomes verbose and scatters related info (response handling vs. tool behavior). Some content (e.g., 'Never display raw JSON') is arguably system-level guidance not specific to this tool.

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?

Given the complexity (external publish, 7 params, output schema), the description covers many aspects: mutation modes, partial failure, idempotency, seat rules, and execution. However, it omits when to choose this over similar siblings (e.g., retraffick_flight) and does not clarify the role of accountId/approvalId/creativeIds. The output schema exists, so return value details are not required, but the missing parameter context lowers completeness.

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?

With 0% schema description coverage, the description must compensate. It explains idempotencyKey (derived retry key) and seatId/seatName (must be explicitly supplied for writes), but it does not clarify accountId, approvalId, or creativeIds. The partial coverage raises it above a 2 but leaves significant gaps.

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 a specific verb+resource: 'push the resulting inactive or approved payload to Yahoo DSP' and includes the complete workflow ('traffick and certify a saved Studio flight, generate or reuse ad-server tags'). This distinguishes it from sibling tools like traffick_flight (which only traffics) or generate_adserver_tag (which only generates tags).

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 provides clear context: it is the 'Publish path for approved work only', and it mentions mutation modes (validate_only, preview_only, execute) and task support ('forbidden'). However, it does not explicitly name alternative tools for non-approved workflows or for steps like generating tags, so it falls short of a 5.

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