undo

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

With no annotations, the description carries the full disclosure burden. It hints at a bounded history ('up to 20') but never states permissions needed, behavior when history is exhausted, whether it is per-design, or that it mutates state — all of which matter for an undo operation.

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?

One short sentence, front-loaded with the core action, with no filler. It is slightly cryptic rather than verbose, but nothing is wasted.

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?

An output schema exists so return values needn't be explained, but for a mutation tool with zero annotations the description is too thin — nothing on the required design argument, failure modes, or scope of what gets reverted.

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% and the single required parameter 'design' is undocumented in both the schema and the description. The agent cannot tell whether 'design' is an ID, a name, or an open-document handle.

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?

States a specific verb and effect: takes back the last change. This is clearly distinguishable from siblings like clear (wipes state) or replace, though the parenthetical '(up to 20)' is ambiguous about whether it is a history limit or a batch capability.

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 guidance on when to use undo versus alternatives such as clear or replace, and no prerequisites (e.g., an open design with existing history). The agent must infer the applicable context from the name alone.

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