I'm currently trying to get the Jetbrains MCP to work with DevoxxGenie and qwen3.
The Jetbrains MCP exports 34 tools with very verbose descriptions, which is too much for the context window of qwen3.

What I'd like to have is a way to do two things:

1. Tick on/off specific tools of a MCP Server. For the Model, it would look like the ticked off Tool simply was never provided.
   This serves two purposes: First, I reduce the amount of tools the Model needs to parse (context window), second I'm able to disable tools that are maybe too powerful (security wise) or are not needed (e.g. I don't want the model to run my code, set breakpoints, etc.)
   I was thinking of something that would look roughly like this (mockup image):

2. I would like to override the description of the tool that is provided to the Model. E.g. the description of the Jetbrains MCP is very verbose, repeatedly mentioning "Jetbrains IDE Editor" etc. I already pasted this into ChatGPT and told it to make it more concise and got a good result that should work. So I want to give the user a way to override the description that DevoxxGenie provides to the Model, so I'm able to adjust that if I feel the need to do so. Of course, users can mess this up if they are not careful.
   I haven't done a mockup for this yet.

I'm willing to try to create a PR for this functionality, but want to be sure that people actually are OK with it being in the plugin to not waste time implementing something that never would be merged.

Your feedback is appreciated!