In what way?

Not sure whats the norm nowadays, but it used to be MCP descriptions were loaded in from the start.

In any case, to be cheaper the `cli --help` command needs to more noisy than the json description.

Finally, and the really big one: cli can be composed with `grep`, `jq` , etc.

This is not true.

I guess it depends on the implementations.

When I use the Atlassian CLI vs their MCP server, I tend to see something like half the token burn with the CLI with more accurate results.

That could be an Atlassian issue but that's the results I'm seeing.

yeah MCP contains a provision for some blocktext for instructions. If your MCP has walls of text in those instructions, it will burn more tokens that a terse MCP.

How do you think the LLM becomes aware of which mcps are available? Vibes?

It depends on the harness. But most use a tool_search tool.

yes and using that tool does what with tokens?

You seem confused.

I'm not. You can build an MCP and throw a ton of junk in there and bloat the shit out of its token cost. So, really, "it depends".