Skip to main content
Glama

cad_modify

Destructive

Change an open CAD model by running a script to create, edit, delete, or save geometry as a single undoable step, then verify the result.

Instructions

Run a script that CHANGES the app's open model (create, edit, delete, save).

Where the app supports it the whole script becomes one undo step, named by summary (a few words the user will see in the app's undo history). Same script rules as cad_read. Verify the result afterwards.

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": {
      "app": "<app>",
      "code": "<code>"
    },
    "name": "cad_modify"
  }
}

Input Schema

NameRequiredDescriptionDefault
appYes
codeYes
summaryNo
instanceNo
timeout_sNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the description earns credit for adding the undo-grouping behavior and how `summary` names the undo entry — information an agent cannot get from annotations. However, it does not disclose what happens on failure, whether partial changes persist, or how timeout interacts with a long script.

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

Conciseness4/5

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

Front-loaded with the mutation scope, then undo behavior, then verification — each sentence adds something. The 'Same script rules as cad_read' cross-reference is compact but depends on knowledge of another tool.

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

Completeness3/5

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

Output schema exists, so return values need no explanation, and the undo/verification guidance is solid. Still, a destructive mutation tool with five parameters at 0% schema coverage leaves `instance` and `timeout_s` unexplained, which is a real gap for correct invocation.

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

Parameters3/5

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

Schema coverage is 0%, so the description carries the full burden. It explains `summary` well and implies `code`/`app` through the script/model framing, but `instance` and `timeout_s` are entirely undocumented in both schema and description.

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?

Uses a specific verb+resource ('Run a script that CHANGES the app's open model') and enumerates the mutations (create, edit, delete, save). The contrast with 'Same script rules as cad_read' makes the read-vs-modify distinction with the sibling explicit.

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

Usage Guidelines4/5

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

Clear context that this is the mutation path and that the result should be verified afterwards, plus a caveat ('where the app supports it') that signals host-dependent behavior. It lacks an explicit 'inspect with cad_read first' routing statement, but the comparison to cad_read gives adequate orientation.

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

Deploy Server

Other Tools