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

Annotations already declare readOnlyHint=false and idempotentHint=true, and the description adds substantial context: billable AI usage, durable execution, mutation modes, partial failure policy, default idempotency key derivation, and seat requirement. These details go beyond what annotations provide and give the agent a clearer picture 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, dense block that mixes essential tool behavior with user-response instructions ('Use assistantSummary first... Never display raw JSON...'). This is not concise, and the structure is poor—there are no clear sections, and the response-formatting guidance is arguably out of place in a tool description. The front-loaded purpose statement is the only well-structured element.

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 tool is complex (27 optional parameters, mutation, several modes), and although an output schema exists, the description does not provide enough guidance on how to select or combine parameters. It only hints at campaign-scoped invocations and seat rules, leaving the agent to guess what inputs are required or appropriate. Important operational details like partial failure and billable usage are covered, but the core 'what to pass' question is unresolved.

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 must compensate, but it only explains a few parameters: campaignId/campaignName, persistence, idempotencyKey, and seatId/seatName. The many other parameters (brief, input, assets, prompt, template, etc.) are left entirely unexplained, so the agent cannot determine their meaning or how to combine them.

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 a specific verb and resource: 'Build and save existing Studio creative records.' It goes on to describe the campaign-scoped build path, which clearly states what the tool does. It also distinguishes itself by noting 'Deprecated alias for build_ad,' directly linking to a sibling tool and clarifying its role as an alias.

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 gives explicit guidance on when to use persistence preview_only ('only for an unsaved ad-hoc preview') and notes that campaign-scoped calls save by default. It also states a critical prerequisite for mutations when multiple seats are authorized (seatId or seatName must be supplied). However, it does not explicitly say 'use build_ad instead' or enumerate exclusions, so it stops short of full alternative guidance.

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