Undo, redo, checkpoints

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

The annotations already mark the tool as destructive and not read-only, and the description adds substantial behavioral context: undo/redo span all changes regardless of author, replies identify what changed, revert preserves every id, and checkpoint reachability is limited to the open project.

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 main actions, then adds only the caveats and distinctions an agent needs. Every clause earns its place, including the id-preservation contrast and the open-project limitation.

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 output schema and annotations, the description covers the remaining decision-critical details: action meanings, label usage, persistence limits, id behavior, and the relationship to `history`. 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?

Schema coverage is 100%, so the schema already documents both parameters. The description still adds meaning by explaining what each action does and how `label` is used for `checkpoint` and `revert`, though it does not add format or validation details beyond that.

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 the specific actions (undo, redo, checkpoint, revert) and the resource state being managed. It also distinguishes the tool from `history` and from duplicating a version, so an agent can identify its role without opening sibling schemas.

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 explains when to use each action and gives explicit constraints: `revert` only works while the project stays open, and `history` lists checkpoints. It also contrasts `revert` with duplicating a version, which is a clear alternative-based guideline.

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