Undo a specific state change, by history event

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

With no annotations provided, the description carries the full burden and succeeds: it flags mutating behavior, reveals that undo appends a new history entry rather than erasing, and discloses the side-effect that lazy expiry/drip housekeeping may persist even for read-like calls. This is strong, honest behavioral disclosure.

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 description is a single, front-loaded paragraph that opens with the key purpose and mutating nature. Each sentence adds a distinct detail (constraints, selection methods, preview, history behavior, side effects), and there is no filler, though it is somewhat dense.

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 complex tool with 5 parameters, no output schema, and nested filter objects, the description covers the essential return signal (`not-latest-event`), side effects, and usage patterns. It does not spell out all possible response fields, but the provided detail is enough to use the tool safely and effectively.

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 80%, so baseline is 3, but the description adds meaning beyond the schema by explaining how `eventIds` come from any tool's `history[].eventId` and how `filter` selects events across items via source/time/attribution. It also contextualizes `preview` as a way to see changes first. Only the `note` parameter receives no added explanation, but the schema covers the main semantics.

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?

The description opens with 'MUTATING TOOL. Revert an item to whatever it was immediately before one of ITS OWN history events', a clear and specific verb+resource statement. It distinguishes itself from the sibling tool `restore` by noting undo works for `kept` and `watching` as well as `lapsed`, which clarifies scope.

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 explicitly states when undo is appropriate, the constraint that only the latest event can be undone, and alternatives like using `filter` for batch operations or `preview` to dry-run. It also references `restore` as the alternate tool for lapsed-state reverts, giving clear when-to-use vs. when-not-to-use guidance.

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