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

With annotations already declaring destructive, non-read-only, and idempotent behavior, the description adds useful context: the action is free, iter0 keeps an exact copy of the prior page, and there are current-page and expiration preconditions. It does not explain token acquisition or error behavior, but it meaningfully adds to the annotation profile.

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 short, front-loads the core action, and every clause adds relevant information: verb, cost, restoration semantics, and preconditions. There is no filler.

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?

The description covers the core behavior and preconditions, and an output schema exists so return values need not be explained. However, for a mutation tool with two undocumented required parameters, the missing explanation of undoToken provenance and designId semantics leaves a meaningful gap.

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 coverage is only 33%; the html parameter is documented in the schema as ignored, but designId and undoToken have no schema descriptions. The tool description implies a design context and an undo token but does not explain where undoToken comes from or what designId must identify, so it does not compensate for the low schema coverage.

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 gives a specific verb and resource: 'Undo the last saved edit from the iter0 card,' and clarifies that it restores the exact prior page. It is clear what the tool does, but it does not explicitly distinguish itself from the sibling restore_version tool.

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 implies when the tool is valid by saying it works only while the edit is the design's current page and the undo has not expired. However, it gives no explicit guidance on when to use this instead of restore_version or other edit-related siblings.

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