dream-creo-mcp

Overview Schema Source Related Servers Discussions Admin

undo

Deletes the newest modeling feature from a named Creo part, or the whole pattern if its newest member is a pattern member, to roll back the last modeling step; confirmation is required.

Instructions

Creates/edits geometry in the running Creo 5 through the DreamFeatureApp plugin. There is no mirror tool: build symmetric shapes with symmetric extrudes, revolves or patterns. Units are mm and degrees. Parts are addressed by name (lowercase, no .prt). Model axes: FRONT is the XY plane (normal +Z), TOP is XZ (normal +Y), RIGHT is YZ (normal +X). Each feature call either ends with an active feature or is rolled back. Nothing is saved unless model_save is called. Check results with model_info (volume, bound_box) and preview_image.

Undo the last modelling step: deletes the newest feature (or the whole pattern if the newest feature is a pattern member). Template datums are never removed. Requires confirm=UNDO.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "<name>",
      "confirm": "<confirm>"
    },
    "name": "undo"
  }
}

Input Schema

Name	Required	Description	Default
`name`	Yes	Part name without .prt
`confirm`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.1.1Nov 6, 2026

TDQS

A4/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses exactly what is destroyed (newest feature, or whole pattern for a pattern member), what is protected (template datums never removed), a hard confirmation gate (confirm=UNDO), and that changes are not persisted without model_save. The remaining gap is what happens when there is no step to undo (error vs. no-op) and whether the deletion is recoverable.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The tool-specific sentence is strong and self-contained, but it is placed after a long generic preamble about units, axes, the absence of a mirror tool, and save semantics that is shared boilerplate rather than undo-specific. Front-loading the undo behavior and trimming unrelated axis/units text would make selection faster; only the pattern-member and save-persistence clauses genuinely earn their place here.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 2-parameter mutation tool with no output schema, the definition covers destruction scope, the confirmation requirement, the persistence caveat, and how to verify the result (model_info volume/bound_box, preview_image). It stops short of describing the return/error surface, which is the one thing an agent cannot otherwise infer.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50%: name is documented in the schema, but confirm has no schema description. The description compensates by giving the exact required literal ("Requires confirm=UNDO"), which is essential information absent from the structured fields. It adds nothing about name beyond the schema, but that is already covered.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Undo the last modelling step: deletes the newest feature" names a concrete verb (undo/delete) and a precisely bounded resource (the newest feature, or the entire pattern if the newest feature is a pattern member). That scope statement ('newest') implicitly separates it from delete_feature, which removes a specifically identified feature, so an agent can route between them without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description makes the use case clear (revert the most recent modelling step) and the rollback boilerplate explains that features either end active or are rolled back. However, it never explicitly says when NOT to use this tool, nor points to delete_feature for removing an older/specific feature, which is the obvious sibling confusion given the tool list.

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