Q7 of 60 — CCA Practice Exam

Structured Data Extraction

Your structured data extraction pipeline uses background subagents to process contracts in parallel — each subagent reads a document, calls an MCP extraction tool, and writes structured output to a staging table. After deploying to production, you notice that roughly 15% of subagent runs terminate silently without producing output. Logs show these failures cluster around contracts that require a clarifying lookup against an external classification API, which the subagents weren't explicitly pre-approved to call. What is the most effective architectural fix?

A. Add a system prompt instruction telling the extraction subagents to skip any contract that requires external classification lookups and flag it for manual review instead.

B. Enumerate the classification API tool in the background subagent's pre-approved tool set before launch, so the permission is granted upfront and the subagent can call it without interruption.

C. Switch all extraction subagents from background to foreground mode so they can surface interactive permission prompts when the classification API tool is needed mid-run.

D. Catch the failed subagent runs at the orchestrator level and automatically retry them with a higher maxTurns value to give each subagent more attempts to resolve the permission issue.