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

The description goes beyond the annotations by disclosing that this writes to Studio, is billable, has partial failure behavior (completed_items_not_rolled_back), and derives deterministic retry keys when idempotencyKey is omitted. It also states the seat requirement for writes and the response-style expectations, giving the agent a thorough understanding of side effects and constraints.

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 block of dense text mixing tool-specific operational details with generic response-style instructions (assistantSummary, raw JSON, IDs). While the information is valuable, it lacks visual structure and repeats orchestration boilerplate that could live elsewhere, making it harder to parse.

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 aspects (synchronous, billable, partial failure, seat requirement, idempotency) and there is an output schema for return values. However, it does not explain what 'refresh brand visuals' actually does functionally—what assets are scraped, how existing visuals are replaced, or what the mutation modes validate_only/preview_only/execute mean—leaving an important functional 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?

The schema has 0% description coverage, and the tool description only mentions idempotencyKey and seatId/seatName. Required parameters like advertiserId, brandName, websiteUrl, and accountId are left entirely to their names. The nested options and storage objects have no explanatory text, so the description fails to compensate for the schema's lack of guidance.

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 opens with the verb+resource 'refresh brand visuals' and immediately clarifies it writes to Studio and creates billable AI usage, distinguishing it from read-only get_brand_visuals. However, it never explicitly differentiates from refresh_brand_profile or explains what a refresh entails beyond the name.

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 states execution is synchronous and task support is forbidden, providing clear when-not guidance. It also gives a concrete prerequisite for mutations (seatId/seatName when multiple seats are authorized). It does not explicitly name alternative tools or scenarios for when this tool is preferred, but the context is clear.

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