MENU
A managed agent deployment for claims triage has grown from 6 tools to 34 tools over 18 months as product teams added capabilities. Triage accuracy has declined from 91 percent to 78 percent, and average tool-selection latency has increased by 2.3 seconds. A junior engineer has proposed adding a tool-router agent in front of the current agent to filter the tool list per request.
Which two findings should you present to justify capability decomposition before adding the router? (Select two.)
Each correct answer presents part of the solution.
Four distinct workflow domains indicate that the agent's responsibilities have expanded beyond a cohesive capability boundary. Decomposing the deployment into domain-focused agents reduces each agent's tool-selection space and produces clearer prompts, permissions, evaluations, and ownership. Option E strengthens this conclusion because placing a model-based router before the existing overloaded agent adds latency, cost, and another failure point without correcting the underlying capability sprawl. Overlapping descriptions should be clarified, while unused tools may simply be removed; neither finding alone proves that separate domain agents are required. Public documentation of a pattern is not evidence that it fits this workload. Anthropic emphasizes simple composable patterns, clearly differentiated tools, and empirical evaluation before adding orchestration complexity. Building Effective Agents