It might be interesting to tie this into something I had a daydream about once and then never bothered to actually do: generate header files from debug info (and then possibly have some LLM tidy it up)
https://github.com/wbenny/pdbex
As for using an LLM to tidy it up... It doesn't seem like there has been a ton of success applying LLM models to reverse engineering yet... A part of me is wondering if this will wind up being a place where the LLM architecture proves insufficient. I'm not an expert but if I had to place a bet I'd bet on diffusion models being more interesting for a lot of reverse engineering use cases. That said, it's not really the same thing, but with Binary Ninja they have a feature called Sidekick that uses an LLM to try to clean up the disassembly; I'm kind of unimpressed but maybe it is useful to somebody.
Its output is kind of ugly, limited by limitations of either the PDB format or Microsoft's terrible parser library, but I've successfully used it for calling functions from a proprietary DLL.
Ghidra also has native functionality to export its data structures, which it can create from DWARF structures (Right click -> Export to C header).
Generating headers and also mutators that you could then modify to meet type constraints was part of that.
Edit: just to add onto the LLM side, I can see this labelling anonymous structs or similar but I'm not sure that's a good idea. What might be interesting would be to try to get an LLM to verbalize/summarize known type constraints for documentation purposes.
I haven't implemented that feature yet because so far I've managed to get by without it. Also, it sounds like a rather deep rabbit hole to fall into and the one I'm currently inside of is big enough as it is.