Every provider in your stack will have a bad day. The difference between an agent that shrugs and an agent that pages you is whether you designed for that day up front.
These posts cover the operational half of agent infrastructure: latency budgets, empty-result handling, retry discipline, and graceful degradation when the premium rung is down.
Your tool chain will break in exactly five ways. Here's what each one looks like in the logs, and what a chain that survives it does differently.
An empty result set arrives as a 200 and gets treated like a 500. The provider didn't fail — it answered. What you do next should depend on whether that answer cost money.
An agent chains tool calls in sequence, and sequences are where tail latency compounds. How to set a budget, split it per call, and spend it on fallback rungs.
Your agent is a distributed system with a single point of failure per dependency. The playbook for staying up when a provider doesn't.