An MCP server doesn't have to have "simple" tools. Having very powerful and effective tools allows you to create great context for the LLM. I don't see any way Skills are better then this; on the contrary, now the "tool executive" is more dependent on the model, introducing non-deterministic context issues.

In the same vein, tools are also easy to iterate on, they are quite simple to implement, and their description is entirely up to you - you can limit how many tokens this description will consume.

This feels like going in the wrong path in a way, but we'll see how this evolves and what are the use cases.