cw_undo

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

With no annotations, the description carries the full burden and does so well: it discloses that undo opens no window, mutates no element, that the observable effect is "none-observed" and that this is the success case rather than a failure. That is exactly the counterintuitive behavior an agent would otherwise misread as an error.

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 critical constraint (expect "none-observed", that is success) is front-loaded and every sentence adds new information. Capitalized emphasis is slightly heavy-handed and the closing sentence is a touch promotional, but nothing is redundant 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?

A zero-parameter, no-output-schema mutation with no annotations is fully covered: what it does, that its observable result is silence, and how to independently confirm the effect. Nothing an agent needs to call it correctly is absent.

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 there is nothing for the description to disambiguate; baseline 4 applies. No missing parameter meaning is possible here.

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 and resource ("Rewind the most recent operation") and scopes it with "the adapter's only rewind," which implicitly separates it from the redo/history siblings. An agent knows exactly what this does without opening a schema.

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 gives a clear usage context (undoing an uncertain write) and a verification procedure (inspect note count or export, not the screen), which is the real 'how to use' guidance. It stops short of explicit when-not-to-use routing to cw_redo/cw_history, so it lands at 4 rather than 5.

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