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

The description goes beyond annotations by disclosing execution mode (synchronous), mutation modes (validate_only, preview_only, execute), partial failure policy (completed_items_not_rolled_back), and idempotency fallback behavior when idempotencyKey is omitted. It also clarifies seat authorization requirements for mutations, which is valuable context not present in the annotations (idempotentHint=true, readOnlyHint=false). This adds meaningful transparency about how the tool behaves, though some statements are generic boilerplate.

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 single dense paragraph containing extensive generic response-formatting rules (e.g., 'Use assistantSummary first', 'Never display raw JSON') that are likely shared across all tools. These non-tool-specific instructions inflate the length and distract from the actual purpose. It is not front-loaded with the most essential information; the business behavior is barely addressed while meta-policy dominates.

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 an 11-parameter mutation tool with nested objects and a business context, the description is largely incomplete. It does not explain what restore_creative_version does, what versionId refers to, how dryRun or expectedVersion affect execution, or what the output means. The output schema exists, so return values are covered, but the human-facing purpose and parameter semantics are under-specified.

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 must compensate for undefined parameters, but it only clarifies idempotencyKey (retry key derivation) and seatId/seatName (required for multi-seat mutations). It doesn't explain accountId, creativeId, versionId, approvalId, changeSummary, expectedVersion, dryRun, or the creative object, which are central to actually invoking the restore operation. Core parameter meanings remain ambiguous.

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 states 'restore creative version' which identifies a specific verb and resource, but it does not explain what 'restore' means in this business context (e.g., undoing changes, recovering an archived version). It lacks differentiation from sibling tools like clone_creative or revise_creative, so an agent cannot fully understand the scope of the 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?

The description provides no explicit guidance on when to use this tool versus alternatives. It mentions 'Task support: forbidden' and 'Mutation modes' but these are operational constraints, not usage scenarios. There is no indication of prerequisites, conditions, or typical use cases that would help an agent decide between restore_creative_version and other creative-related mutations.

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