wb_live_undo

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

No annotations are supplied, so the description carries the full burden. It does disclose the most important behavioral trait — dry-run by default, destructive only with apply=true — but says nothing about reversibility (whether the undone action can be redone), permission/auth needs, or what the preview result contains.

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?

Two short sentences, front-loaded with the action and then the safety default. No filler, though the phrasing "Preview/history check" is slightly ambiguous about whether it returns history or performs a check.

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, no output schema, and 0% schema coverage, so the description is the only information source — and it omits the meaning of the required rpc_dir, the timeout, and what a preview returns. Inadequate for a three-parameter mutation tool with zero structured support.

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 description coverage is 0%, so the description must explain all three parameters; it explains only apply and leaves the required rpc_dir and timeout entirely undefined. The one parameter it does cover is handled well, but a required, undocumented string parameter is a significant gap.

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?

Specific verb+resource: "Undo one World Builder history action" states the operation and the unit of scope (one action). It implicitly separates itself from the sibling wb_live_redo, but never names it, so an agent must infer the pairing.

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?

"Preview/history check unless apply=true" tells the agent the default is a non-destructive dry run and that apply=true commits the undo — that is real when-to-use guidance. It gives no guidance on when to use undo vs. wb_live_redo, wb_live_history, or how many steps back one call moves, so usage context remains partial.

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