Hacker News Reader

Comment by ramesh31 | Hacker News Reader

Tools are the only thing that matters, and are what you should focus on, not "agents" as a separate concept. Locking yourself into any particular agent framework is silly; they are nothing but LLM calling while-loops connected to JSON/XML parsers. Tools define and shape the entirety of an agent's capability to do useful things, and through MCP can be trivially shared with virtually any agentic process.

View on HN

Yes, I wonder if it ever makes sense to partition an agent's toolkit across multiple "agents"—besides horizontal scaling. Why should one process have access to APIs that another doesn't? Authorization and secrets, maybe, but functionality?

Depending on the capability or context size of the model, it is easy to imagine a situation where specifying too many tools (or MCPs) can overwhelm it, affecting the accuracy.

> it is easy to imagine a situation where specifying too many tools (or MCPs) can overwhelm it, affecting the accuracy.

Answer to this is agent explorable interfaces a la HATEOAS. Define a single entry point to your MCP gateway and give the agent clues to drill down and find what it needs to use.

You may get some mileage out of protocols like Agent Network Protocol (ANP), Agent Interaction & Transaction Protocol (AITP), Agora "Protocol Documents" (PDs), agents.json, Airweave, or the Coral Protocol.

AITPs "message passthrough pattern" supposedly enables "progressive" delegation—where a general agent can forward requests to specialized agents.

agents.json may facilitate a sort of progressive disclosure across the "flows" and "links" of multi-step workflows that an agent is guided through, wherein subsequent actions or information is revealed as dependencies are met, limiting upfront information overload.

I've only skimmed the barest details of these protocols, guided by this paper: https://arxiv.org/html/2504.16736v2

Reply on news.ycombinator.com