undo

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

Annotations only provide readOnlyHint=false, so the description carries most of the behavioral load and does so well: it says the mutation reverts paragraphs to their prior state and discloses a guard condition (refused if edited since). This is meaningful preconditions context beyond the annotation, though it doesn't describe the failure/return behavior.

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 tight sentences that lead with the core action and follow with the default-scope and precondition. No filler; minor room to sharpen the differentiator from sibling tools.

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 mutation tool with no output schema and a non-readOnly annotation, the description covers the action, scope, and the key safety precondition. It stops short of explaining the result or error surface, but is adequate 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 75% and the schema already documents the op_id default ('the latest in effect'), which the description largely restates. The description adds no meaning for 'expect' (sha256) or 'dry_run' beyond the schema, so it neither compensates nor regresses.

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 (take back / undo) and resource (a logged batch or restore), plus the concrete effect of returning paragraphs to their prior state. It is clear on its own, though it doesn't sharply differentiate from the sibling 'restore' tool, which could be mistaken for it.

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 the default selection rule ('the latest one that is still in effect by default') and a precondition ('Refused if they were edited since'), which imply when the call is valid. However it never names the alternative tools (restore, history_list) or states explicitly when to prefer this over them.

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