undo

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

No annotations are supplied, so the description carries the full behavioral burden and does not meet it. It leaves open whether repeated calls walk back through an undo stack, whether the undo itself is reversible, whether it requires an open project, and what happens when there is nothing to undo.

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 intent is front-loaded in a single short sentence with zero preamble. The Japanese mirror is a locale convenience rather than added information for the agent, a minor redundancy but not harmful.

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 zero-parameter, no-output-schema operation the description is nearly sufficient, but because nothing else (annotations or schema) describes behavior, the unanswered questions about stack depth and no-op behavior leave it only minimally complete.

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 tool takes zero parameters and the schema is empty, so there is nothing for the description to disambiguate. Baseline 4 applies.

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?

"Undo the last edit" states a specific verb and target state, so the agent knows exactly what it does. It does not differentiate from siblings (e.g. edit_notes, delete_notes), but no redo/alternative tool is presented that would require an explicit split.

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?

Usage is only implied – an agent can infer this is the recovery path after a mistake. There is no statement of when it applies vs. manually reverting via edit_notes, nor any prerequisite such as an open project or an existing edit history.

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