To validate that your reduced toolset still covers all functionality, run these prompts against your agent. If the agent succeeds using the new tools, your reduction is a success.

Category 1: High-Level Observability & Health

• "Show me the topology of the bookinfo namespace."

• "Are there any unhealthy namespaces in my mesh right now?"

• "Give me a status report on the interaction between Kiali and Istio components."

Triggering this tag here is appropriate if you want to verify the agent can visualize the output of get_mesh_graph.

Category 2: Troubleshooting & Debugging

• • "Why is the productpage service returning 500 errors?"

• • • Expected Flow: get_metrics -> get_logs.

• • "Analyze the latency for the reviews workload over the last 30 minutes."

• • • Expected Flow: get_metrics -> get_traces.

• • "I see a spike in duration for ratings. Can you check the traces to see which span is lagging?"

Category 3: Istio Configuration & Management

• • "List all VirtualServices in the default namespace and check if they have any validation errors."

• • • Expected Tool: manage_istio_config (action='list').

• • "I need to shift 50% of traffic to v2 of the reviews service. Apply a patch to the existing VirtualService."

• • • Expected Tool: manage_istio_config (action='patch').

• • "Create a Gateway named my-gateway in the istio-system namespace."

• • • Expected Tool: manage_istio_config (action='create').

Category 4: Resource Inspection

• • "List all workloads in the bookinfo namespace that have missing sidecars."

• • • Expected Tool: get_resource_details.

• • "Get the full details and health status for the details service."