checkpoint_rewind

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

Annotations already flag destructiveHint=true and idempotentHint=false, so the safety profile is covered. The description adds genuine value beyond that by disclosing exactly what is destroyed: the target checkpoint 'and every later checkpoint', plus the default-target 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?

One sentence, front-loaded with the destructive verb 'Undo', with the scope and default packed in without filler. Every clause earns its place.

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 destructive, non-idempotent single-param tool with no output schema, the description covers the action, the default target, and the collateral scope. It could still note that the undo is itself not trivially reversible, but the annotations carry the risk signal.

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% and the single parameter 'id' is undocumented in the schema. The description compensates by explaining that id refers to a checkpoint and that omitting it defaults to the latest checkpoint.

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?

Names a specific action (restore/undo) and resource (files at a named checkpoint), and states the scope includes the named checkpoint plus every later one. It is clearly distinguishable from checkpoint_list, the only nearby sibling.

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?

It explains the default (latest checkpoint when no id is given) and the blast radius of the operation, but never states when to prefer this over alternatives (e.g. checkpoint_list to inspect first) or any precondition. Usage is implied rather than prescribed.

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