rollback

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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description goes well beyond them: it names exactly what is destroyed ('everything done after it is lost'), explains the surprising post-state (the open file becomes the checkpoint copy), and warns the user to Save As first. It also discloses the query-mode behavior when `name` is omitted.

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?

Three tight sentences with the destructive consequence front-loaded in the first clause, followed by the Save As warning and the no-argument fallback. Every sentence carries distinct information; nothing is padded.

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 single-optional-param, no-output-schema tool, the description covers destruction semantics, the mutation of the open file, the required Save As step, and the no-name listing behavior. It is close to complete; only the meaning/format of a valid checkpoint `name` and any error behavior are unaddressed.

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 0%, so the description carries the full burden, and it does so by defining the two modes of the single `name` parameter: present = roll back to that checkpoint, absent = no rollback and a checkpoint listing is returned. It never clarifies the expected name format (e.g., checkpoint label vs. index), leaving one 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?

States a specific verb and resource ('Return to a checkpoint of this file') and makes the effect unambiguous: the file reverts and later work is discarded. It contrasts semantically with the sibling 'checkpoint' by describing the destructive inverse, but never names an alternative tool, so it falls just short of a 5.

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 clear operating context: call with `name` to roll back, call without `name` to list checkpoints, and a workflow warning ('use Save As before you save'). It does not explicitly frame when to choose this over the related checkpoint/diff_since tools, so no exclusions are stated.

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