I don’t mind schemas and repositories, but I feel it’s a bit backwards. That’s the kind of work I would hope we can avoid with AI.

MCP is written for the AI we’ve got not the ones doing all the hyping want us to believe exists.

With a long enough context window it wouldn’t matter the difference. But “long enough” in this context to me means where you view its length as big enough where size no longer matters. Kind of like modern hard drives that are “big enough that I don’t care about a 1gb file” (I was thinking megabyte files but that might be too large of an order of magnitude )