Agents And Tool Use easy
The model emits three parallel tool calls in one turn: get_weather, get_flights, and get_hotels. get_hotels takes 4 seconds longer than the others. How should the host respond?
- A Send the two fast results back immediately and append the hotel result in a later turn.
- B Return only the first result that finishes, since the model can re-request the others.
- C Run the three calls one after another so the results always arrive in a fixed order.
- D Wait for all three to finish, then return every result together in the next request.
Answer: D. Wait for all three to finish, then return every result together in the next request.
With **parallel tool calls**, the model expects a result for every call it issued in the same follow-up message; partial returns (A) leave dangling calls and confuse or break the conversation. The tradeoff is that the turn is as slow as the slowest tool. Running them sequentially (C) only makes sense when one call's output is needed as another's input.
One system design question a day, with spaced repetition so the ones you miss come back.
Get the appRelated questions
- You are defining a 'schedule_meeting' tool for an agent. Which schema decision most reduces wrong or malformed calls?
- A model emits three parallel tool calls: `get_inventory`, `get_price`, and `get_shipping`. To cut latency, the host appends each result to the transcript as it arrives and immediately re-invokes the model. Runs start failing with malformed-request errors, and some produce hallucinated shipping costs. What should the host do?
- A team splits a coding agent into planner, coder, tester, and reviewer agents, and each receives the full transcript of the previous agent. The expected quality gains did not appear. Cost tripled, and the reviewer often fixates on approaches that earlier agents abandoned. When is a multi-agent split actually justified?
- A support agent should remember each customer's preferences across months of sessions. The team appends every past session summary to the system prompt. After six months, prompts exceed 80,000 tokens, latency has doubled, and the agent sometimes ships to an address the customer replaced weeks ago. What redesign fixes both problems?
- A teammate proposes splitting a single coding agent into five agents, arguing that more agents means smarter results. When is a multi-agent split actually justified?
- A data-analysis agent runs model-generated Python inside the same container as your API service. That container has database admin credentials in environment variables. A security review flags this as critical. What is the best mitigation?