Comment by jun_lung
4 days ago
Because why should you have to load "here's how to update this skill!" information into the context window every time you use it? Would you expect the agent to go to that URL and look for more recent skill files every time you use it? Is this a real question?
Versus having an agent read MCP config and fetch the existing tools every time it wants to use the MCP? It's duplicate functionality.
The agent doesn't do that. The harness does the fetching and provides the tool definitions to the agent without the agent having to do anything.
Nothing says that agents can't read skills, interpret them and fetch stuff. Needing to agent to pass things off to powerful LLMs to interpret doesn't have to be done for everything.