undo_last_patch

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

Annotations already indicate destructiveHint=true, so the description carries less burden. It adds the mechanism of using recorded compare-before-write metadata, but does not disclose potential failure modes (e.g., no patches to undo) or require an active edit session. This is a minimal value-add beyond annotations.

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 sentence that front-loads the verb 'Undo' and provides the essential action and context. There is no redundancy or unnecessary detail.

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 tool with one parameter, the description is minimal but not complete. It lacks an explanation of the parameter, does not mention prerequisites like an active edit session, and does not describe return values or errors. The sibling context helps, but the description alone is barely adequate.

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?

The schema has one parameter (editSessionId) with no description (0% coverage). The description mentions 'edit session' but does not explicitly explain that editSessionId is the identifier for the session or how to obtain it. This leaves the parameter semantics unclear.

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 action (Undo), the target (latest patch), and the context (edit session). It also mentions the mechanism (compare-before-write metadata), which distinguishes it from the sibling tool apply_memory_patch.

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 usage in the context of an edit session but does not explicitly state when to use it versus alternatives. There is no mention of conditions like 'after an unintended patch application' or exclusions.

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