It has to be suited for human consumption too though.

I wonder if this has any real benefits over just doing very simple html wireframing with highly constrained css, which is readily renderable for human consumption. I guess pure text makes it easier to ignore many stylistic factors as they are harder to represent if not impossible. But I'm sure that LLMs have a lot more training data on html/css, and I'd expect them to easily follow instructions to produce html/css for a mockup/wireframe.

LLMs are surprisingly good at extracting data from other data, so at the end of the day there is no right or wrong, it's what works best for you use case.