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

The description adds substantial behavior beyond annotations: creates billable AI usage, durable execution, partial failure policy (completed_items_not_rolled_back), idempotency key derivation, and seat requirements for multi-seat mutations. These complement the readOnlyHint=false and idempotentHint=true annotations without contradiction. Minor gap: no mention of versioning or effect on previous creative versions.

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 front-loads the core purpose but then shifts to a list of system-level instructions that may apply globally across tools (e.g., 'Never display raw JSON', 'Use assistantSummary first'). The structure is a single run-on block with punctuation errors ('review.. Classification'). While each sentence adds some value, the overall message is more verbose than necessary for a tool description.

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?

For a mutation tool with an output schema, the description covers mutation behavior, failure policy, idempotency, seat handling, and output expectations. It does not need to explain return value structure since an output schema exists. The main missing piece is usage differentiation from sibling tools, but operational context is quite 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 0% schema description coverage, the description needed to compensate, but it only explains idempotencyKey and seatId/seatName requirements. The required creativeId, along with prompt, instructions, persistence, saveToStudio, dryRun, expectedVersion, accountId, and approvalId, receive no semantic explanation. This forces the agent to rely on parameter names and types, which is insufficient for nuanced options like the persistence enum.

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-object: 'Revise an existing saved Studio creative from plain-language instructions, save the updated creative, and return fresh preview links plus QA/certification context.' This clearly states the tool's purpose and result. It also differentiates from siblings like clone_creative or create_creative_version by focusing on revision of existing saved creatives.

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 does not provide explicit guidance on when to use this tool versus alternatives such as clone_creative, create_creative_version, or retraffick_creative. It describes mutation constraints and seat requirements, but lacks contextual triggers or exclusions. The agent must infer usage scope solely from the name and purpose statement.

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