Arguing web architecture with myself

A while ago, talking about web sites as web services in the context of "Ten Future Web Trends," I said:

My guess is that tooling will gradually have more and more useful stuff baked in, so that when you put up, say, a list of favorite books it will be likely to have whatever "book" microformatting is appropriate without your doing too much on your part. For example if you copy a book title from Amazon or wherever, it should automagically carry stuff like the ISBN and the appropriate tagging.

Um, why copy book data? This is the web. Make a link with the book title for text, pointing at Amazon or wherever. Anything crawling around the web trying to make sense of this ought to be able to recognize where the link is pointing, chase it and get the other data. All the usual arguments against copying (e.g., difficulty of keeping copies in sync) apply.