You've configured the system so that all four subagents have access to the complete set of
18 tools. During testing, agents frequently call tools outside their specialization - the synthesis agent attempts web searches, and the report generator tries to analyze documents. What is the primary cause of this poor tool selection behavior?

• A. Choosing from 18 tools instead of 4-5 relevant ones increases decision complexity beyond reliable selection thresholds.
• B. The agents' role descriptions in their system prompts conflict with having access to tools outside that role.
• C. The tool definitions consume too much context window space, leaving insufficient room for task content.
• D. The coordinator cannot track which capabilities each subagent has, leading to misrouted tasks.

You are building a structured data extraction system using Claude. The system extracts information from unstructured documents, validates the output using JSON schemas, and maintains high accuracy. It must handle edge cases gracefully and integrate with downstream systems.
Your invoice extraction uses tool use with strict JSON schemas. JSON syntax errors never occur, but 12% of extractions fail semantic validation--for example, line-item amounts do not sum to the extracted total, or vendor IDs do not match valid formats. These failures currently route to manual review.
What is the most effective approach to reduce manual-review volume while maintaining accuracy?

• A. When validation fails, make a follow-up request containing the document, extraction, and validation errors so the model can correct the result.
• B. Implement post-processing logic that automatically corrects common errors, such as recalculating totals from line items when sums do not match.
• C. Add stricter schema constraints with detailed field descriptions to prevent the model from initially generating invalid values.
• D. Retry the extraction up to three times when validation fails, accepting the first result that passes validation.

Which factor MOST directly affects API cost?

• A. Internet speed
• B. Number of processed tokens
• C. CPU clock frequency
• D. Screen resolution

A customer returns 4 hours after the initial session about the same billing dispute. The previous
32-turn session contains lookup_order results showing "Status: PENDING, Expected resolution:
24-48 hours." In testing, you observe that when resuming sessions with stale tool results, the agent often references the outdated data in responses (e.g., "I see your refund is still being processed") even after subsequent fresh tool calls return different information. What approach most reliably handles returning customers?

• A. Resume with full history and configure the agent to automatically re-call all previously-used tools at session start to ensure data freshness.
• B. Start a new session, inject a structured summary of the previous interaction (issue type, actions taken, resolution status), then make fresh tool calls before engaging.
• C. Resume with full history and add a system prompt instruction telling the agent to always prefer the most recent tool results when multiple calls to the same tool exist in context.
• D. Resume with full history but filter out previous tool_result messages before resuming, keeping only the human/assistant turns so the agent must re-fetch needed data.