rollback

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

With no annotations, the description carries the full burden and does well: it discloses the destructive data loss ('everything done after it is lost'), the side effect that the open file becomes the checkpoint copy, and the no-op behavior when `name` is omitted. It stops short of covering permissions or what exactly the returned checkpoint list looks like.

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 sentences, all front-loaded with the destructive effect first, then the side-effect warning, then the default behavior. Every sentence adds information; phrasing is slightly dense but never 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 one-parameter mutation tool with no annotations and no output schema, the description covers the destructive consequence, the file-state side effect, and the return content in the no-arg case. It is essentially complete; the only minor gap is what constitutes a valid checkpoint identifier.

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% and the single `name` parameter has no schema-level description, so the description must compensate and largely does: it defines both the supplied case (rollback to that checkpoint) and the omitted/null case (list checkpoints, no mutation). Only the expected string format/identifier convention for `name` is left unstated.

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 immediately scopes the effect ('everything done after it is lost'). It is clearly distinguishable from the creation-side sibling 'checkpoint', though it never names that sibling, so the differentiation is implied rather than explicit.

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 explains the two operating modes ('without `name` nothing is rolled back: the answer lists the checkpoints'), which is genuinely useful conditional guidance, and the Save As warning implies a save-flow precondition. However, it never states when to rollback versus alternatives like diff_since or run_spec, nor any hard prerequisite such as having a checkpoint to begin with.

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