Skip to main content
Glama
communitycad-mcp

communitycad-mcp

Official

Upload a new version

upload_version

Publish a new version of your own model after explicit confirmation, with real change notes and an updated README when dimensions or usage change.

Instructions

Upload a new version of the user's own model. Only after the user's explicit yes. Write real notes on what changed, and refresh the README when dimensions changed. Nothing is sent when the notes or README fall short.

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": {
      "model_id": "<model_id>",
      "path": "<path>",
      "notes": "<notes>"
    },
    "name": "upload_version"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesThe new CAD file, or a folder to upload as a ZIP.
notesYesWhat changed, at least 20 characters.
model_idYesThe user's own model (id or page URL).
readme_markdownNoThe refreshed README (same sections as upload_model). Send it when dimensions or usage changed.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.2

TDQS

A4.3/5.0
Behavior4/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=true), the description discloses the human-confirmation requirement and a server-side validation gate ('Nothing is sent when the notes or README fall short'). That gate is real behavioral information an agent would otherwise not anticipate and prevents wasted calls. It stops short of saying whether the rejection appears as an error or a silent no-op.

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?

Four short sentences, front-loaded with the action, followed by the confirmation rule and the quality conditions. Nothing is padded, though 'Nothing is sent when the notes or README fall short' is slightly ambiguous about the rejection mechanism and could be stated more precisely.

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 4-parameter mutation with no output schema, the definition covers the safety gate, the quality bar, and the conditional README refresh, which is enough to invoke it correctly. It leaves open what is returned on success (version number? URL?) and how a failed validation surfaces to the caller.

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 100%, so the baseline is 3, but the description adds genuine meaning: 'notes' must be substantive ('Write real notes on what changed') and 'readme_markdown' is conditional on dimension or usage changes, clarifying when the optional param should be sent. It does not explain the 'path' ZIP-vs-file choice, which the schema already covers.

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?

States a specific verb and resource ('Upload a new version of the user's own model') and scopes it to the user's own model, which separates it from a first-time publish path like upload_model. An agent immediately knows this is a versioning write on an existing model, not a creation or edit.

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?

Gives a hard precondition — only after the user's explicit 'yes' — and a conditional rule for the README ('refresh ... when dimensions changed'). It does not name the sibling to use for a brand-new model or for metadata-only edits, but the confirmation gate is explicit and actionable.

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