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

The description richly discloses behaviors beyond annotations: it states the tool writes to Studio, creates billable AI usage, publishes externally, is synchronous, has a partial failure policy (completed_items_not_rolled_back), derives an idempotency retry key when omitted, and requires seatId/seatName for mutations. 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 verbose and mixes tool capability, operational constraints, and response-formatting instructions in a dense block. The first sentence is a run-on with multiple clauses, and while most sentences add value, the lack of clear separation between concerns makes it less scannable than ideal.

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?

The description covers key operational context: execution modes, synchronous execution, task unsupported, partial failure policy, idempotency, seat requirements, and response handling. An output schema exists, so return value details are not necessary. However, with 42 parameters and 0% schema coverage, the lack of parameter explanation and the missing explicit pointer to launch_creative_campaign hold it back from full 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?

Schema description coverage is 0%, so the description must compensate for the 42 parameters, but it only explains idempotencyKey, seatId/seatName, and execution modes. Most parameters (objective, brand, audience, KPI, etc.) remain semantically undefined, and many have nested structures that are not explained, leaving a significant gap for agent invocation.

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 name 'launch_creative_campaign' combined with the description clearly states it launches creative campaigns, with details about preview, collaborate, operate, and publish modes. It distinguishes itself from siblings by explaining that default preview mode works without Studio while operate creates Studio work, and it identifies itself as a deprecated alias for launch_creative_campaign.

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 explicit guidance on when to use different execution modes (preview, collaborate, operate, publish) and states 'Task support: forbidden' as a limitation. It names the canonical alternative (launch_creative_campaign) by calling itself a deprecated alias, but does not explicitly instruct to prefer that sibling. Seat authorization requirements are also clearly stated for mutations.

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