create_dovetail

Instructions

Implementation Reference

• src/sketchup_mcp/tools.py:159-187 (handler)

  The create_dovetail tool handler function. It is decorated with @mcp.tool() and delegates to _call() with the Ruby command name 'create_dovetail' and all parameters (tail_id, pin_id, width, height, depth, angle, num_tails, offset_x, offset_y, offset_z).

  @mcp.tool()
  async def create_dovetail(
      ctx: Context,
      tail_id: Annotated[str, Field(min_length=1)],
      pin_id: Annotated[str, Field(min_length=1)],
      width: Annotated[float, Field(gt=0)] = 50.0,
      height: Annotated[float, Field(gt=0)] = 50.0,
      depth: Annotated[float, Field(gt=0)] = 15.0,
      angle: Annotated[float, Field(gt=0)] = 15.0,
      num_tails: Annotated[int, Field(gt=0)] = 3,
      offset_x: float = 0.0,
      offset_y: float = 0.0,
      offset_z: float = 0.0,
  ) -> str:
      """Create a dovetail joint between two components. Dimensions in mm."""
      return await _call(
          ctx,
          "create_dovetail",
          tail_id=tail_id,
          pin_id=pin_id,
          width=width,
          height=height,
          depth=depth,
          angle=angle,
          num_tails=num_tails,
          offset_x=offset_x,
          offset_y=offset_y,
          offset_z=offset_z,
      )

• src/sketchup_mcp/tools.py:160-172 (schema)

  Input parameter schema for create_dovetail. Parameters include tail_id (str, min_length=1), pin_id (str, min_length=1), width (float>0, default 50.0), height (float>0, default 50.0), depth (float>0, default 15.0), angle (float>0, default 15.0), num_tails (int>0, default 3), offset_x/y/z (float, default 0.0). All dimensions in mm.

  async def create_dovetail(
      ctx: Context,
      tail_id: Annotated[str, Field(min_length=1)],
      pin_id: Annotated[str, Field(min_length=1)],
      width: Annotated[float, Field(gt=0)] = 50.0,
      height: Annotated[float, Field(gt=0)] = 50.0,
      depth: Annotated[float, Field(gt=0)] = 15.0,
      angle: Annotated[float, Field(gt=0)] = 15.0,
      num_tails: Annotated[int, Field(gt=0)] = 3,
      offset_x: float = 0.0,
      offset_y: float = 0.0,
      offset_z: float = 0.0,
  ) -> str:

• src/sketchup_mcp/tools.py:159-159 (registration)

  The @mcp.tool() decorator registers create_dovetail as a FastMCP tool. The 'mcp' instance is imported from sketchup_mcp.app (file src/sketchup_mcp/app.py, line 14)

  @mcp.tool()

• src/sketchup_mcp/tools.py:21-50 (helper)

  The _call() helper function that all tools delegate to. It acquires a connection via get_connection(), calls send_command(name, kwargs), handles errors, and unwraps the MCP response format.

  async def _call(ctx: Context, name: str, **kwargs) -> str:
      """Dispatch a tool call to SketchUp and shape the response for Claude.
  
      - Connection errors → human-readable string, server keeps running.
      - SketchUpError → ``format_error`` string.
      - Successful MCP-shaped result ({content: [{text: "..."}]}) → just the text.
      - Any other dict result → ``json.dumps``.
      """
      try:
          sketchup = await get_connection()
      except ConnectionError as e:
          return f"SketchUp not running or extension not started: {e}"
      try:
          result = await sketchup.send_command(name, kwargs)
      except ConnectionError as e:
          # Cached connection was stale and reconnect inside send_command failed:
          # `_connect_or_raise` re-raises OSError as ConnectionError before the
          # send/recv try-block, so it escapes past the SketchUpError handler.
          return f"SketchUp not running or extension not started: {e}"
      except SketchUpError as e:
          return format_error(e, debug=config.LOG_LEVEL == "DEBUG")
      content = result.get("content") if isinstance(result, dict) else None
      if (
          isinstance(content, list)
          and content
          and isinstance(content[0], dict)
          and "text" in content[0]
      ):
          return content[0]["text"]
      return json.dumps(result)