undo

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

The destructiveHint annotation already flags mutation, and the description adds further behavioral detail: the undo covers manual changes, requires the current revision, and should be preceded by state inspection. This gives useful context beyond the annotation.

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 short sentences with no filler. The core operation is stated first, followed by the essential precondition, and every phrase adds value.

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 simple destructive operation, the description conveys the essential workflow—inspect state, require current revision, undo last change. However, it leaves the agent to infer which session is 'selected' and how to obtain the current revision, and no output schema means error/return behavior is absent.

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 0%, so the description must compensate. It only indirectly hints at expectedRevision via 'requires current revision' and at sessionId via 'selected editor,' without naming either parameter or explaining how to obtain their values. This is insufficient for an agent to confidently supply both required parameters.

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 and resource: undo the selected editor's last change. The phrase 'including manual changes' clarifies scope beyond the name alone, and the operation is clearly distinct from siblings like edit_entities, edit_terrain, and session inspection tools.

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?

Explicitly says to inspect state first and to require the current revision, providing a clear precondition and workflow cue. It does not need to name alternatives because no sibling tool performs undo, but it also does not explicitly state when not to use it.

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