Same topic, related formats. Practice these next.
Explain the principle that agent tools should be atomic. Describe two problems that arise from composite tools (tools that bundle multiple operations together).
Atomic tools do exactly one thing, so the agent gets one Observation per step. That makes failures easy to attribute and retries safe to repeat.
Imagine teaching a new cook by handing them recipe steps. If you give one giant card that says cook the whole meal and it goes wrong, you have no idea which part failed, and redoing it might burn the parts that were already fine. Now give them small cards instead: chop the onion, boil the pasta, add the sauce. When one card fails, you know exactly which step broke, and you redo only that step without ruining the rest. Agent tools work the same way. A tool that does one clear thing returns one clear result, so the agent can look at it, understand what happened, and decide the next move. A tool that bundles five things together returns one fuzzy result, and the agent is left guessing what actually went right or wrong.
Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example. Click to expand.
Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example.
Everything important, quickly.
Define atomic versus composite, then give the two headline problems with concrete tool names: error attribution from one Observation per bundle, and broken idempotency when a read and write share a tool. Close with the granularity tradeoff and why names, schemas, and structured errors drive correct tool selection.
Real products, models, and research that use this idea.
What an interviewer would ask next. Try answering before peeking at the approach.
Red flags and common mistakes that signal junior thinking. Click to expand.
Bundling many operations into one tool to save round trips, then losing the ability to tell which internal step failed or to retry one step safely.
The night-before-the-interview bullets. Scan these on the way to the call.
Primary sources. Skim if you want the original framing.