Skip to main content
Glama

Protogen CAD

Generate cad design

generate_cad_design

Generate a parametric CAD design contract in a ProtoGen workspace.

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": {
      "workspace_id": "<workspace_id>",
      "part_name": "<part_name>",
      "dimensions_mm": "<dimensions_mm>"
    },
    "name": "generate_cad_design"
  }
}

Input Schema

NameRequiredDescriptionDefault
featuresNoOptional. Features such as holes or fillets.
materialNoOptional. Material. Default aluminum.aluminum
part_nameYesName of the part.
request_idNoOptional. Your id for this call. Repeat it to retry safely: the same request_id is never charged twice.
payment_refNoOptional. A paid credit or payment reference, used only after the free daily calls. Leave it out to use the free tier or a seat.
workspace_idYesThe workspace id returned by create_cad_workspace.
design_intentNoOptional. What the part is for.
dimensions_mmYesOverall dimensions in millimetres, for example {"length": 120, "width": 40}.
output_formatsNoOptional. Formats to prepare: openscad, step_contract, manufacturing_brief.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changed
    • addedInput schema / properties / design_intent / description
      Added value: +"Optional. What the part is for."
    • addedInput schema / properties / dimensions_mm / description
      Added value: +"Overall dimensions in millimetres, for example {\"length\": 120, \"width\": 40}."
    • addedInput schema / properties / features / description
      Added value: +"Optional. Features such as holes or fillets."
    • addedInput schema / properties / material / description
      Added value: +"Optional. Material. Default aluminum."
    • addedInput schema / properties / output_formats / description
      Added value: +"Optional. Formats to prepare: openscad, step_contract, manufacturing_brief."
    • addedInput schema / properties / part_name / description
      Added value: +"Name of the part."
    • addedInput schema / properties / payment_ref / description
      Added value: +"Optional. A paid credit or payment reference, used only after the free daily calls. Leave it out to use the free tier or a seat."
    • addedInput schema / properties / request_id / description
      Added value: +"Optional. Your id for this call. Repeat it to retry safely: the same request_id is never charged twice."
    • addedInput schema / properties / workspace_id / description
      Added value: +"The workspace id returned by create_cad_workspace."
  2. Changed2 schema fields changed
    • addedInput schema / properties / payment_ref
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Payment Ref"
      +}
    • addedInput schema / properties / request_id
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Request Id"
      +}
  3. First observed

TDQS

C2.9/5.0
Behavior2/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=false and idempotentHint=false, so the safety profile is covered. The description adds only that the output is a 'contract' rather than a file, and says nothing about credit consumption, the free daily tier, or what happens on retry — all of which live only in the schema's parameter text.

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?

A single front-loaded sentence with no filler, which is structurally clean. It is arguably undersized for a 9-parameter generative tool, but nothing in it is wasteful or buried.

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

Completeness2/5

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

For a credit-consuming generative tool with nested objects and 9 parameters, one sentence leaves significant gaps: no mention of the async/contract nature of the result, no workflow relationship to create_cad_workspace or export_cad_design, and no billing guidance. The presence of an output schema excuses return-value detail, but not the missing operational context.

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 description coverage is 100% across all 9 parameters, including the features, material, dimensions_mm, request_id and payment_ref semantics. The description contributes no additional parameter meaning, so the baseline 3 applies.

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

Purpose4/5

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

The description names a specific verb ('Generate') and a specific artifact ('a parametric CAD design contract') scoped to a ProtoGen workspace, so an agent can tell it apart from export_cad_design or create_cad_workspace. It stops short of explicitly contrasting with those siblings, keeping it below a 5.

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

Usage Guidelines2/5

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

There is no guidance on when to use this instead of export_cad_design or manufacturing_plan_from_spec, nor any stated prerequisites beyond the implicit workspace requirement. The agent must infer the workflow ordering from the schema's 'returned by create_cad_workspace' note.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.