I tried doing the MCP approach with about 100 tools, but the agent picks the wrong tool a lot of the time and it seems to have gotten significantly worse the more tools I added. Any ideas how to deal with this? Is it one of those unsolvable XOR-like problems maybe?
There are many routes to a solution.
Two options (out of multiple):
- Have sub-agents with different subsets of tools. The main agent then delegates. - Have dedicated tools that let the main agent activate subsets of tools as needed.
AI agents can't even remember which files are already in the context, let alone them picking right tool for the job.
You wind up having to explicitly tell it to use a tool and how to use it (defeating the point, mostly)
congrats, you have encountered one of the fundamental flaws of using an ad-lib generator as an orchestration / rules engine.
Remove most tools. After 30 tools it greatly regresses.
[dead]