undo_write

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

With no annotations, the description carries the full burden and does a good job: it flags the write nature, explains the before-image mechanism, shows the side effect of recording an action.reverted entry, and offers dryRun preview. It could also mention failure cases like having no undoable write, but most key consequences are disclosed.

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?

Four concise sentences, tightly packed with distinct facts. The WRITE marker is front-loaded, followed by behavior, invocation options, and side effects. No fluff or repetition.

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?

For a tool with two optional parameters and no output schema, the description covers main behavior, selection of the write to undo, preview mode, and a side-effect. It doesn't describe the shape of the preview plan or behavior when no undoable write exists, but overall the agent has enough to call it correctly.

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 baseline is 3. The description adds real meaning beyond the schema by explaining the omission behavior for actionId and the purpose of dryRun. This is a meaningful contribution, though params are simple.

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?

Description states a specific behavior: "Reverses a recorded write" using the ledger's before-image, and gives concrete outcomes (restore updated task, delete created task). It is not a tautology and is distinct from related action-recording and action-listing tools.

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?

The description clearly explains when to omit actionId, when to pass dryRun, and that actionId comes from list_actions. It does not explicitly mention when not to use it or name an alternative tool, but the guidance is sufficient for a focused undo operation.

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