My experience with email is that people have subject lines, email explicitly identifies to and cc recipients; email is threaded; email often has quotes/excerpting/highlighting from prior parts of the thread.
On the other hand, most chat usage I see is dependent on temporal aspects for threading (people under-utilize platform features for replies etc), tagging is generally only done to ping people to attract attention, chat groups are frequently reused for multiple different purposes.
Leaping to a point-in-time within a chat stream is often a bad user experience, with having to scroll up and down through unrelated stuff to find what you’re looking for.
Stuff in email is just massively more discoverable for me.
This obvious assumes that who ever wrote the email isn't a madman, who insist on using emails like it was a chat.
While all of these features could in principle be realized in a chat system as well, in practice they don’t provide that flexibility and power.
Another usability feature of emails is that they have a subject line. This allows to meaningfully list emails in a compact fashion. In a desktop interface, you can easily view and visually grep 50 emails or more at once in a mail folder or list of search results (in something like Outlook or Thunderbird or Mutt). This allows working with emails more efficiently than with a chat view where you can only see a few messages at once, and only of the same thread or channel.
Yet another usability feature of emails is that each email has its own read/unread status. This, again, is facilitated by each email being its own separate data object, and by the separation between subject and body, which allows the read status to be unambiguously bound to “opening” the email, or to navigating in the list of emails alongside a preview pane. And you can mark any email as unread again. In chats, the granularity of read/unread is the whole chat, whether you’ve actually read all of it or not. You can’t easily track what you’ve read or not in an automated way as with email, other than by that coarse-grained linear time-based property of when you last visited the channel.