I have discovered the the BEST way to get 3D modeling results from LLMs
The app LiDAR scans the room while taking hundreds of high quality photos.
Then a workflow + skill I've created models out every item recursively checking the model against the photo at the exact spot +
If you are building ANY sort of visual builder - you must implement WebMCP calls
Watch how natural this type of voice input is when tool calls are fast
this is done in realtime, no edits