Undo this session's changes

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

Annotations already flag destructiveHint=true and readOnlyHint=false, but the description adds meaningful behavioral detail: reverse-order reversion, backed-up files being restored, created files moved to a trash folder, and GUI settings restored. This goes beyond the annotations and helps the agent understand the concrete effects.

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, front-loaded sentence that covers the core action and its main effects without redundancy. Every clause contributes useful 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?

Given the presence of an output schema and destructive annotations, the description is largely complete: it explains scope, ordering, file restoration, and trash behavior. The main gap is the lack of comparison to sibling tools like cm_restore.

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 accepts zero parameters, so there are no parameter semantics to explain. The baseline for a parameterless tool is 4, and the empty schema is consistent with the description.

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 states a specific verb and scope: undoing every change made in this server session, including workspace values, model parameters, files, and GUI settings. It is clear about what the tool does, but does not distinguish itself from related sibling tools such as cm_restore.

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 phrase 'this server session' implies the context for use, but there is no explicit guidance on when to choose this tool over alternatives like cm_restore or when not to use it. The usage is inferable but not stated.

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