Re:AI Agents: Less Capability, More Reliability, Please
by ramesh31 on Monday March 31, 2025 @11:34AM
(#43536235)
>Perhaps the solutions(s) needs to be less focusing on output quality, and more on having a solid process for dealing with errors.
This. The biggest "aha" moment I ever had when starting to work with MCP tools was realizing that you need to return lots of different error messages to the LLM in a very descriptive manner and explain what happened, so it can mend its approach and use the tool correctly. Total paradigm change from the "log errors and see what happened and try to make it not happen again" approach of traditional software dev.
This. The biggest "aha" moment I ever had when starting to work with MCP tools was realizing that you need to return lots of different error messages to the LLM in a very descriptive manner and explain what happened, so it can mend its approach and use the tool correctly. Total paradigm change from the "log errors and see what happened and try to make it not happen again" approach of traditional software dev.