I have created Agent system with 3 subagents as tool. I have cleary given instructions to a subagent to use a tool to get the information from the tool but it's not working.

I have declared a root_agent which is supposed to follow the workflow but after triggering the first agent, it stops there. Below is the instruction of my root_agent. You are a manager of a care home. Your primary task is to help the staff member creating an event by analyzing and classifying the description provided by staff. Your workflow: 1. **Validate the event description**: Ensure that the description is clear and contains all necessary information (e.g., name or initials of resident/staff/manager, date, location (optional), etc.). If the description is unclear or missing critical information, provide feedback to the user. To do this use the `event_validator` tool. 2. **Extract relevant information**: If the event description is valid, extract key details such as the eventType(can be `resident` or `staff`) and names of residents or staff mentioned. Use the `event_information_extractor` tool for this task. If no resident or staff is found, return an error message to the user. 3. **Classify the event**: Based on the extracted information, classify the event using the `event_classifier` tool.

Hi Brandon and all other members. I recently started learning about Agents and luckily found this amazing community. I hope I can learn a lot from you people and will try to share my little knowledge with all.

I have created an Agent system using ADK which has one manager which is managing other agents as sub agents. So, when the manager delegates to agent A, i want to return to the main agent and then continue the process.

🚀 Big Announcement In just 10 days (Friday, September 27) we’re officially launching something I’ve been waiting to share with you for a long time. It’s called Shipkit.ai. 👉 You can pre-order today and lock in $100 off before launch 💡 Why I built Shipkit.ai Over the past few years I’ve taught thousands of developers through my YouTube channel (75,000+ subscribers) and inside my community (nearly 10,000 members). I kept seeing the same roadblocks stop good ideas from ever shipping: - Which stack should I choose? - How do I connect all the pieces? - I built a demo on my laptop… but how do I deploy a real product people can actually use? Advice helps, but it isn’t enough. Developers don’t just need tips — they need working projects. 🛠️ What Shipkit.ai gives you Shipkit.ai gives you everything you need to go from idea → production-ready AI app. You’ll start with working templates for the most common AI applications: - AI chat - RAG - ADK workflows Shipkit walks you through each one step by step so you know exactly how to customize and launch it as your own. No guesswork. No dead ends. Just shipping. The course inside Shipkit shows you every stage of the journey: - Idea → Development plan - Plan → Working code - Code → Deployed application in production And at every step, you also get prompt templates that show the AI how to take action for you. These help you move faster and avoid getting stuck so you can focus on shipping real applications instead of wrestling with the process. ✅ Proof it works Shipkit.ai was built with Shipkit. To prove it, I used the RAG template inside Shipkit to build this very platform. That means you’re not just getting theory — you’re learning from the exact system that produced Shipkit.ai itself. The same step-by-step process that takes you from: - Idea → Plan - Plan → Code - Code → Production