Revert recent actions in SolidWorks design documents. Easily undo the single last operation or reverse up to twenty steps by specifying the file path and the required step count.
Undo the last operation(s).
| Name | Required | Description | Default |
|---|---|---|---|
| doc | No | Document title or path. Defaults to the active document. | |
| steps | No |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false and destructiveHint=false, so safety is covered; the description adds only that multiple operations can be reverted, matching the 'steps' parameter. It does not say whether undo is document-scoped, session-scoped, bounded by an undo history, or what happens when there is nothing to undo. With annotations carrying the safety profile, this is adequate but thin.
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?
A single front-loaded sentence with zero padding – nothing to trim. The terseness reflects under-specification rather than wasteful writing, which is penalised in the other dimensions.
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 state-mutating editing tool with no output schema and a partially documented schema, one sentence leaves key questions unanswered: the granularity of an 'operation' (feature, sketch edit, property change), behavior when the stack is empty, and whether the result is reported. More explanation is warranted here.
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 coverage is 50%: 'doc' is documented in the schema, but 'steps' has no description and its 1–20 bound and default of 1 appear only as raw constraints. The description's '(s)' hints that multiple steps are possible but never explains the cap, default, or whether undo can span documents.
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?
Specific verb ('Undo') plus resource ('the last operation(s)'), so the agent knows exactly what action is taken. It does not differentiate from neighbouring tools like sw_replay_journal or sw_delete_feature, which is the only thing keeping it from a 5.
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?
There is no guidance on when to use undo versus alternatives such as sw_delete_feature, sw_replay_journal, or sw_set_suppression, and no stated preconditions (e.g., an open document with a non-empty undo stack). The agent must infer all routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.