Presumably you can iterate on and manually tweak the design first, which is much quicker and less cumbersome than iterating on and tweaking the design when it's in clunky HTML/CSS/JS form and all the non-vector graphical assets are flattened/cropped etc.

Good point. There are emerging tools that focus on AI UI creation workflow like https://stitch.withgoogle.com/

I find it to be sometimes easier to utilize my Figma library to design what I want as I generally don't have to do rework. It gets annoying after awhile to waste tokens and context dealing with stupid small things like "Hey, the icon in the icon button is wrong." if you do prompting. Pulling in the same icon & icon button through a MCP is generally easier.