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

Beyond the annotations (readOnlyHint false, idempotentHint true), the description discloses 'creates billable AI usage,' 'Execution: synchronous,' 'Task support: forbidden,' mutation modes (validate_only, preview_only, execute), 'Partial failure policy: completed_items_not_rolled_back,' and the idempotency key derivation behavior. These are significant behavioral traits not captured in annotations.

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 unrelated operational guidance (response handling, user interaction style) with tool semantics. It repeats the title content, contains a typo ('Studio inventory..'), and could be significantly shortened without losing value. It is not front-loaded with the most critical information.

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?

It provides substantial context on usage, mutation modes, failure policy, and output handling, and the output schema covers return values. However, the complete absence of parameter semantics for 25 parameters is a major gap, especially given the tool's complexity, so the description is not fully complete.

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 25 parameters and 0% schema description coverage, the description carries the burden but mentions no parameter meanings except idempotencyKey in the retry context. Required fields like campaignName, objective, audience, KPI, and funnelStage are left undefined, so the description fails to compensate for the schema's lack of descriptions.

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 'Plan and create an initial Studio creative set for a campaign that has no saved creatives,' specifying the verb, resource, and scope. It also explicitly distinguishes itself from build_ad by saying not to use it for rebuilding existing creatives, which sets it apart from 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?

It gives explicit when-to-use context ('campaign that has no saved creatives') and when-not-to-use: 'Do not use this tool to rebuild existing creatives; use build_ad with campaignId or campaignName.' It also marks itself as a 'Deprecated alias for build_campaign_creative_set,' signaling an alternative.

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