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

The description goes far beyond the annotations, disclosing 'writes to Studio, creates billable AI usage', synchronous execution, mutation modes, partial failure policy, deterministic retry-key derivation, and seat-authorization requirements. These are substantive behavioral traits not inferable from the readOnly/idempotent/destructive hints alone. No contradiction with 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 a long, run-on paragraph that repeats the title and mixes tool semantics with generic agent response style instructions ('Use assistantSummary first', 'Never display raw JSON'). This is not concise; it could be trimmed to a few sentences without losing essential 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?

The description covers operational context well (permissions, mutation modes, partial failure, idempotency, seat requirements) and notes the returned JSON is internal state. However, it is incomplete regarding the meaning and formats of the 27 input parameters. The output schema exists but does not compensate for the parameter documentation gap.

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 27 parameters and 0% schema description coverage, the description carries full responsibility for explaining parameters. It clarifies only seatId/seatName, idempotencyKey, creativeIds, and persistence (via 'saveToStudio'). The vast majority of parameters—brief, input, assets, prompt, audience, campaign, template, advertiser, objective, requestedFormats, etc.—are left undefined, which is a serious gap.

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 'Generate Studio-ready design briefs for one or more creatives' with a specific verb, resource, and scope. It also distinguishes itself by noting it is a 'Deprecated alias for create_creative_brief', which immediately differentiates it from the canonical sibling tool.

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 explicitly names the alternative tool ('Deprecated alias for create_creative_brief') and provides concrete when-to-use conditions: 'When creative IDs and saveToStudio are supplied... otherwise it returns a non-destructive proposal.' It also mandates seatId/seatName for any mutation when multiple seats are authorized, giving clear operational guidance.

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