---
title: "Comment by Kartik N V J K on \"A2A + MCP: Building Self - Orchestrating Multi-Agent Workflows on AWS Serverless\" | Hashnode"
description: "The 5 tools at 95% versus 30 tools at 48% number is the one I keep coming back to, because it reframes tool overload as a measurable accuracy cliff rather than"
url: "https://hashnode.com/posts/a2a-mcp-building-self-orchestrating-multi-agent-workflows-on-aws-serverless/6aba458389b9459d40d5b494/comment/6ababbee1ca73c08cbffcc5c"
---

[Discussion](https://hashnode.com/posts/a2a-mcp-building-self-orchestrating-multi-agent-workflows-on-aws-serverless/6aba458389b9459d40d5b494)

Comment [A2A + MCP: Building Self - Orchestrating Multi-Agent Workflows on AWS Serverless](https://hashnode.com/posts/a2a-mcp-building-self-orchestrating-multi-agent-workflows-on-aws-serverless/6aba458389b9459d40d5b494)

[Kartik N V J K](https://hashnode.com/@kartik-nvj)

[Sep 28](https://hashnode.com/posts/a2a-mcp-building-self-orchestrating-multi-agent-workflows-on-aws-serverless/6aba458389b9459d40d5b494/comment/6ababbee1ca73c08cbffcc5c)

The 5 tools at 95% versus 30 tools at 48% number is the one I keep coming back to, because it reframes tool overload as a measurable accuracy cliff rather than a vague smell. Splitting into special-purpose agents helps, but it moves the risk to the handoff, which is where I see most multi-agent systems actually break. I wrote up how I vet MCP servers before trusting them in an agent, the same trust concern from the tool side: [kartiknvjk.hashnode.dev/how-i-evaluate-mcp-server…](https://kartiknvjk.hashnode.dev/how-i-evaluate-mcp-servers-for-security-before-i-trust-them) . Did accuracy recover once each sub-agent was back down to a handful of tools?