Undo

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

The description goes well beyond annotations by explaining synchronous versus asynchronous undo semantics, verification state, the effect on parametric timeline features, and the exact return signal when no undo is possible. These details are material for a mutating operation that annotations mark as non-read-only and non-idempotent.

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 definition is front-loaded with the core action and then tightly covers the design-type branches and return behavior. Every sentence carries operational information, and the parenthetical details add useful precision rather than clutter.

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 no-parameter undo tool with no output schema, the description supplies the behavioral details an agent needs: design-type handling, return states, and the recommended confirmation path for asynchronous undo. Nothing essential for correct invocation is 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?

The tool has zero parameters and schema coverage is 100%, so there is no parameter meaning for the description to add. The baseline for a no-parameter tool is appropriate here.

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 a specific action and scope: 'Step the design back one operation.' It immediately distinguishes parametric versus direct design behavior and explains the effect on timeline features, so an agent can distinguish this from deletion or suppression tools.

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?

Usage context is clear, including when there is nothing to undo and when to confirm asynchronous results with get_scene_info. It does not explicitly compare against sibling tools such as suppress_feature or delete_all, so it falls short of full alternative-routing guidance.

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