Agents And Tool Use easy
An internal agent has grown to 120 tools, many with overlapping names like search_docs, find_docs, and query_docs. Wrong-tool errors are rising. What is the best next step?
- A Add even more specialized tools so that every possible request has an exact matching tool.
- B Consolidate overlapping tools and expose only the subset relevant to the current task.
- C Raise the sampling temperature so the model explores more tools before committing.
- D Keep all 120 tools but move their descriptions to the end of the prompt to save attention.
Answer: B. Consolidate overlapping tools and expose only the subset relevant to the current task.
More tools dilute selection: overlapping descriptions make the choice ambiguous and every schema costs prompt tokens. Consolidating and scoping tools per task trades some coverage for accuracy. Adding specialized tools (A) helps only when a needed capability is truly missing, not when the existing set is already confusable.
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?