I've been building agents for a bit (RA.Aid OSS coding agent, now Gobii web browsing agents).
The main problem with MCP is that it just makes tools available for the agent to use. We get the best performance when there's a small set of tools and we actively prompt the agent on the best way to use the tools.
Simply making more tools available can give the agent more capabilities, but it can easily trash performance.
The main problem with MCP is that it just makes tools available for the agent to use. We get the best performance when there's a small set of tools and we actively prompt the agent on the best way to use the tools.
Simply making more tools available can give the agent more capabilities, but it can easily trash performance.