You are building a multi-agent research system using the Claude Agent SDK.

Vendor: Anthropic
Product: CCAR-F
Update on: Aug 26, 2026
Questions: 152

Anthropic CCAR-F Question Answer

You are building a multi-agent research system using the Claude Agent SDK. A coordinator agent delegates to specialized subagents: one searches the web, one analyzes documents, one synthesizes findings, and one generates reports. The system researches topics and produces comprehensive, cited reports.

The document-analysis agent has a single analyze_document tool that takes a document and a free-text instruction parameter. During evaluation, requests such as “extract the key financial metrics” often return narrative summaries, while “summarize the methodology” sometimes returns raw data tables. The synthesis agent reports that 35% of analysis results require new requests with clarified instructions.

What is the most effective way to improve reliability?

Enhance the tool description with detailed examples showing how different instruction phrasings should map to different output formats.

Split the generic tool into purpose-specific tools—extract_data_points, summarize_content, and verify_claim_against_source—each with defined input and output contracts.

Keep the single tool but add an analysis_type enum parameter requiring explicit selection between extraction, summarization, and verification modes.

Have the coordinator pre-classify each analysis request before passing instructions to the document-analysis agent.