Undo, redo, checkpoints

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

The annotations declare only the destructive/read-write profile. The description adds valuable behavior beyond that: undo/redo step through changes made by anyone, the reply names what changed, checkpoints persist with the project and survive saving, and revert preserves every id unlike duplication. This meaningfully improves the agent's understanding of side effects and results.

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 front-loaded with the action list and then explains the less obvious actions (checkpoint, revert). It is appropriately sized for a four-action tool, though the revert/duplication clause is somewhat dense and could be tightened.

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?

Given the tool has four actions, a 100%-covered schema, and an output schema, the description is nearly complete. It covers persistence, id preservation, and reply behavior, but does not explicitly warn that revert discards later changes or state whether checkpoints can be removed, leaving minor gaps for a destructive tool.

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 already 100%, so the schema documents both parameters. The description still adds meaning by tying each action enum value to its effect (e.g., checkpoint remembers this point, revert undoes back to it while keeping ids) and clarifying how label is used. It does not add syntax or edge-case detail for the parameters.

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 names four specific actions (undo, redo, checkpoint, revert) and explains what each does, including the alternate framing 'name where the plan is now and come back to it.' It also distinguishes this tool from the sibling history tool and from duplicating a version. This gives an agent a clear, distinct purpose.

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?

It explicitly points to `history` for listing checkpoints and contrasts revert with duplicating a version ('a copy renumbers'), which helps choose the right tool in those cases. However, it does not state general when-to-use or when-not-to-use guidance for undo/redo versus other edit tools, leaving some inference to the agent.

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