Undo last action

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

With no annotations, the description carries the full burden and does well: it discloses the snapshot mechanism, that the operation is best-effort (may not fully succeed), and its session/target-frame scope. It does not describe the return signal (success vs. partial failure), which matters for a best-effort 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?

Three dense sentences with zero filler. The core action leads, and the constraints follow in priority order (limits, then session scope).

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?

No annotations and no output schema, so the description must carry behavior, limits, and scope — and it largely does. The remaining gap is the response shape for a best-effort operation, which an agent would want before relying on it.

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 tool takes zero parameters, so the baseline is 4. The description correctly adds no parameter noise and instead spends its words on behavior and scope.

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 (reverses) and a precisely scoped resource (the most recent auto-captured mutating action), plus implementation hints (snapshot-based, best-effort). It never names the obvious siblings redo or restore_checkpoint, so an agent gets no explicit differentiation from those.

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?

Gives real conditions for use and non-use: only within the current plugin session, only for actions executed through this bridge, and explicitly cannot restore deleted nodes or structural changes. It stops short of naming redo or restore_checkpoint as the alternatives for those cases, so routing still requires inference.

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