Undo

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

The description warns that the action may revert changes made by the user, which is meaningful behavioral transparency beyond the destructiveHint annotation. It does not fully detail side effects like interaction with save state, but for a simple undo operation this is adequate.

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 brief and front-loaded, with the core purpose in the first sentence. The Ctrl+Z analogy conveys behavior efficiently, and the Args line is directly tied to the parameter without unnecessary prose.

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 simple undo operation, the explanation is functionally complete: it states the action, the target, the parameter, and the key caveat about user edits. It does not enumerate every edge case, but the output schema exists and the behavior is well modeled by the Ctrl+Z analogy.

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 schema provides only a type and default for 'steps', but the description adds a plain-language explanation: 'How many steps to undo.' This clarifies the parameter's meaning and likely range of use, though it does not specify edge cases like zero or excessive values.

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 clearly states the tool undoes recent actions in Visio, using the Ctrl+Z analogy which is immediately understandable. It also names the exact resource (Visio's undo stack) and distinguishes this from other document modification tools in the sibling list.

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 a clear usage frame ('exactly as Ctrl+Z would') and adds an important caveat that the undo may revert the user's own last edit rather than the agent's. It does not explicitly contrast with alternatives, but no other sibling tool performs undo, so the guidance is sufficient.

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