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

The description goes well beyond the annotations (which only indicate it's a write, idempotent, and non-destructive). It reveals that execution is synchronous, mutation modes include validate_only/preview_only/execute, partial failures are not rolled back, and a deterministic idempotency key is derived if omitted. It also mandates seatId/seatName for multi-seat writes. These are rich behavioral details that help an agent understand side effects and error handling.

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 overcrowded with generic response-formatting instructions (assistantSummary, raw JSON, mention IDs only when useful) that are not specific to this tool and could be global boilerplate. While the action and key behavioral traits appear early, the critical idempotency and seat rules are buried at the end. The structure could be tightened by separating tool-specific facts from generic response guidelines.

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?

Despite having an output schema and annotations, the description does not clarify the core cloning semantics: what exactly is cloned, how creativeId points to the source, or what approvalId, expectedVersion, and dryRun do. With 8 parameters and 0% schema coverage, an agent would struggle to invoke the tool correctly. The added operational details are helpful but not sufficient to make the description 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?

Schema description coverage is 0%, so the description must explain parameters. It partially explains idempotencyKey (derived if omitted) and seatId/seatName (required for multi-seat mutations), but leaves creativeId, accountId, dryRun, approvalId, and expectedVersion entirely unexplained. This is insufficient for an agent to correctly populate required parameters like creativeId.

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 'clone creative', which is a specific verb+resource pair that clearly indicates the tool's action. It is distinct from sibling tools like archive_creative or create_creative_version. However, it does not elaborate on what cloning entails (e.g., whether it duplicates an existing creative into a new one), leaving some ambiguity about the exact operation.

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?

No explicit guidance is provided on when to use clone_creative versus alternatives such as create_creative_version or retraffick_creative. The description mentions 'Task support: forbidden' but this is a constraint, not usage guidance. There is no mention of scenarios, prerequisites, or when another tool would be more appropriate.

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