Agents And Tool Use easy
Your team wants several different agent hosts to use the same internal ticketing tools without writing a custom integration for each host. Where does the Model Context Protocol (MCP) fit?
- A It is a protocol for exposing tools and resources so any compatible host can call them.
- B It is a specialized model that decides which tool to call before the main model responds.
- C It is a vector database that stores tool outputs so agents can reuse results across hosts.
- D It is a fine-tuning format that teaches each model the schemas of your internal tools.
Answer: A. It is a protocol for exposing tools and resources so any compatible host can call them.
**MCP is a protocol**, not a model: an MCP server exposes tools and resources once, and any compatible host can discover and call them. The tradeoff is running and securing a server process versus maintaining N bespoke integrations. Thinking of it as a routing model (B) is the common confusion; tool selection is still done by the host's LLM.
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?