With your narrow definition of the problem and reduction of communication down to pure utilitarian exchange of information between two parties that are willing to put in the effort to get the required context from the public domain - your argument is strong.

I don't believe that it holds true in context of typical communication between humans. You need to include the additional text to save people time looking things up, make the story flow better, fit in within the expected style of writing for intended audience etc.

To me the problem with LLM writing is not that someone is sending me 700kb of information I can get elsewhere, but that they didn't invest the time to understand what would be useful for me as a reader. I don't need 700kb of generic slop, but I probably need additional 300kb of relevant publicly available info to help me understand the purpose of the new information being sent.

In my opinion, not understanding the reader is exactly why bad writers remain bad writers - LLM doesn't know who the document is written for exactly.