undo

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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false), and the description adds a genuinely useful behavioral guarantee beyond them: it refuses when the file changed since the target change, so newer work is never lost. That refusal condition is the key trait an agent needs and is not in the structured fields.

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?

Two tight sentences with zero filler. The selection logic is front-loaded and the safety constraint follows, making it easy to scan.

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?

With an output schema present and annotations covering the safety flags, the description supplies the remaining critical context (id source, default selection, refusal-on-conflict). Only the relationship to sibling restore_version is left implicit.

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 100%, so the schema already documents all three parameters, including that an empty change_id means 'undo the latest'. The description's note about the id coming from recent_changes largely restates schema content, so baseline 3 is appropriate.

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 (undo) and resource (a change), and clarifies the two selection modes: a specific change id or the latest change. It does not explicitly differentiate itself from the sibling restore_version, so it falls 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?

The description implies when to use it by pointing to recent_changes as the id source and explaining the default-to-latest behavior, but it never states when to prefer undo over siblings like restore_version or versions, nor any exclusions.

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