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

The description goes far beyond annotations by disclosing synchronous execution, partial failure policy, mutation modes, idempotency key derivation, and the mandatory seatId/seatName for writes in multi-seat scenarios. This adds rich behavioral context that readOnlyHint, idempotentHint, and destructiveHint do not convey. No contradictions 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 long and dense, with a clear front-loaded purpose but includes extensive response-formatting instructions (e.g., 'Use assistantSummary first', 'Never display raw JSON') that are not directly about tool selection or invocation. The repeated canonical field list also duplicates schema information. While each sentence has some value, the description is less concise than ideal.

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 critical behavioral aspects like mutation modes, partial failure policy, idempotency, and seat requirements, making it fairly complete for a complex mutation tool. Since an output schema exists, return values need not be described. However, it omits potential prerequisites or error scenarios and leaves patch field semantics partially unexplained. Overall, it is quite comprehensive but not exhaustive.

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 schema description coverage at 0%, the description must compensate for undocumented parameters. It partially does by listing canonical patch fields and explaining idempotencyKey behavior and seatId/seatName requirements. However, it does not describe the semantics of most patch fields (e.g., targetAudience, creativeBrief, sizes) or required parameters like accountId and patch beyond their names. The description adds some value but leaves significant gaps.

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 the tool updates a Studio campaign, using a specific verb and resource. It differentiates from update_flight and update_advertiser by naming 'Studio campaign', but does not explicitly contrast with sibling tools. The canonical field list reinforces the purpose but does not add sibling differentiation.

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 implies usage for modifying existing campaigns ('Update a Studio campaign') but does not explicitly state when to use it versus create_campaign or archive_campaign. It provides guidance on which fields to patch but lacks explicit when-to-use or when-not-to-use instructions relative to alternatives.

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