Undo a specific design operation while preserving unrelated later edits. Conflicting changes fail safely; undo the undo to redo.
Guarded undo of a specific operation, preserving unrelated later edits. Conflicting changes fail safely. Undo the resulting undo operation to redo.
| Name | Required | Description | Default |
|---|---|---|---|
| actor | Yes | ||
| documentId | Yes | ||
| operationId | Yes | ||
| expectedRevision | Yes | ||
| targetOperationId | Yes |
Changes observed during successful MCP inspections.
v0.1.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate destructiveHint=true and readOnlyHint=false, and the description adds valuable behavioral context: it preserves unrelated later edits, fails safely on conflicts, and supports redo by undoing the undo. This goes beyond the annotations without contradicting them. It does not detail error modes or permissions, but given annotation coverage the added context is strong.
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 dense sentences with no filler. The core purpose is front-loaded, followed by an important behavioral guarantee and a concise redo instruction. Every sentence earns its place and the definition remains scannable.
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 five required parameters, zero parameter descriptions, and no output schema, the description does not fully equip an agent to construct a valid call. The ambiguous operationId versus targetOperationId relationship is particularly consequential. The tool's core conflict-safety behavior is described, but critical parameter semantics and expected failure responses are missing.
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 for five undocumented required parameters. It provides general concepts like 'guarded' and 'target operation,' but it never explains the distinction between operationId and targetOperationId, nor the role of expectedRevision or actor. This leaves an agent guessing at critical parameter semantics.
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 resource: a 'guarded undo of a specific operation.' The qualifiers 'preserving unrelated later edits' and 'conflicting changes fail safely' clearly differentiate this operation-level undo from snapshot_restore or history_read. Even without naming siblings, an agent can distinguish this tool's unique role.
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 the tool: for targeted undo of one operation while preserving unrelated edits. The instruction 'Undo the resulting undo operation to redo' gives useful sequential guidance. However, it does not explicitly state when not to use it or name alternative tools for full-document rollback or read-only history inspection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.