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

Discloses many behavioral traits beyond the annotations: 'Classification: creates billable AI usage,' 'Execution: durable,' 'Mutation modes: validate_only, preview_only, execute,' and 'Partial failure policy: completed_items_not_rolled_back.' It also explains the deterministic idempotency key derivation and the explicit seat requirement for mutations. No contradiction with annotations; in fact, it enriches the idempotentHint.

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 block of text, mixing tool behavior with agent output instructions ('Never display raw JSON...'). It is front-loaded with the purpose and then provides operational details, but it is verbose and could be tightened by removing user-response guidance that is not directly about tool invocation.

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 tool's complexity (27 parameters, output schema present), the description provides a high-level overview, critical operational modes, idempotency, and seat rules. However, it omits how to perform ad-hoc builds without a campaignId, how to specify individual creative/asset parameters, and how the output schema is structured. The output schema covers return values, but the parameter semantics gap leaves it incomplete.

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?

The description clarifies only a handful of 27 parameters (campaignId/campaignName, persistence, seatId/seatName, idempotencyKey) in context. With schema description coverage at 0%, the description is expected to compensate but leaves the majority of parameters (brief, assets, input, template, requestedFormats, skipTraffickedRebuild, etc.) unexplained. The mention of 'saved brief, approved asset set' implies resolution via campaignId, but direct parameter semantics are largely absent.

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 'Build and save existing Studio creative records' and explains the campaign-scoped behavior. It explicitly notes 'Deprecated alias for build_ad,' which distinguishes it from sibling tools like build_campaign_creative_set and leanriq_build_agent_ad. This is a specific verb+resource statement with clear scope.

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 usage context: 'Campaign-scoped calls save by default; use persistence preview_only only for an unsaved ad-hoc preview.' It also directs users to build_ad via the 'Deprecated alias' note. However, it does not explicitly compare against all sibling build/create tools or state absolute exclusions beyond the deprecation, so a bit more alternative guidance would elevate it.

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