Request business rewind

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

Annotations already indicate destructiveHint=true, and the description's mention of 'rewind' implies mutation and potential data loss. It adds context about re-execution but does not elaborate on specific effects like what state is affected or if the operation is reversible.

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, clear sentence at 14 words. It is front-loaded with the action 'Request a rewind'. No extraneous content, though it could be slightly more structured with separate clauses.

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?

Given the tool's destructive nature, complexity of parameters, and relationship to siblings, the description is insufficient. It lacks usage context, does not explain the rewind-to parameter's options, and provides no guidance on when to rewind instead of using alternative flow controls.

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?

With 0% schema description coverage, the description should compensate but only vaguely references 'last stable point or checkpoint' for one parameter. It ignores the reason and message parameters, offering no additional meaning beyond the schema.

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 clearly states the tool requests a rewind to a stable point or checkpoint, which is a specific action that distinguishes it from sibling tools like abort or resume. However, it could explicitly differentiate from siblings.

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 provides no guidance on when to use this tool versus alternatives like flow.abort or flow.pause. It lacks any context about appropriate scenarios or prerequisites.

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