creative_update_preview

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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is fully covered structurally. The description adds nothing beyond restating 'preview' — it does not say what the preview returns (a diff? validation errors?), whether it validates the payload, or that it leaves state unchanged. No contradiction with annotations, but no value added.

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?

A single short sentence with nothing extraneous, so it is not bloated. However, its brevity comes at the cost of under-specification rather than efficiency — the same length could have carried one clarifying clause about the preview's effect.

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 four-required-parameter, nested-payload mutation-preview tool, the description omits the essentials: what the preview returns, whether it is a dry-run against the referenced creative, and how it relates to the eventual apply step. An output schema exists, which relieves some burden on return values, but the workflow context is still missing.

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 100%, so all four parameters including the nested payload are documented in the schema, which sets the baseline at 3. The description adds no semantics of its own — notably it does not mention that the payload only accepts 'name' with additionalProperties=false, a constraint the agent would only find by reading the schema.

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 names a verb ('Preview') and a resource ('creative update'), so the basic operation is inferable. But it does nothing to separate this tool from the many adjacent preview siblings (creative_create_preview, creative_delete_preview, ad_update_preview, campaign_update_preview), leaving the agent to rely on the name alone.

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?

There is no guidance on when to call this versus creative_get, creative_create_preview, or the corresponding apply operation. The agent must infer the preview-then-apply workflow from the naming convention rather than from the description.

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