When designing an agent to interact with a backend database, it is critical to distinguish between access failures and valid empty results.
Which of the following statements correctly describe handling these scenarios? Choose 2 correct answers.

• A.An access failure (e.g., database timeout) should return isError: true so the agent knows the check was not actually performed.
• B.An access failure should silently return an empty array C] to smoothly transition to alternative tools.
• C.A valid empty result (searched successfully, but no matches) should return isError: false.
• D.Both access failures and empty results should throw fatal exceptions to the coordinator to halt execution.

Comment: *

Name: *

Email: *

Verification: *

According to best practices, which of the following scenarios should trigger a developer to use Plan Mode in Claude Code? Choose 2 correct answers.

• A.When implementing multi-file architectural changes.
• B.When adding a single console. log statement to a known file.
• C.When evaluating multiple valid approaches for a new feature implementation.
• D.When fixing a minor typo in project documentation.

Comment: *

Name: *

Email: *

Verification: *

A developer at builds an MCP server to standardize repetitive actions for the engineering team. They want to provide ready-to-use message sequences with specific formatting instructions that bypass the need for users to write them from scratch. Which MCP component fulfills this requirement?

• A.MCP Subagents
• B.MCP Prompts
• C.MCP Tools
• D.MCP Resources

Comment: *

Name: *

Email: *

Verification: *

A properly structured SKILL.md file relies on YAML frontmatter metadata to inform Claude of its capabilities. Which of the following are REQUIRED fields in the skill frontmatter? Choose 2 correct answers.

• A.name
• B.description
• C.allowed-tools
• D.model

Comment: *

Name: *

Email: *

Verification: *

During testing, you find that when a customer says "I need a refund for my recent purchase," the agent calls process _refund immediately - but populates the required order_id parameter with a plausible-looking but fabricated value instead of first calling lookup_order to retrieve the actual order ID. The refund call fails because the fabricated ID doesn't exist. Which change directly addresses the root cause of the agent fabricating the order_id value?

• A.Switch tool_choice from "auto" to "any" to force the agent to make a tool call on every turn.
• B.Update the process_refund tool description to explicitly state that order_id must be obtained from a prior lookup_order call and must never be assumed or invented.
• C.Pre-parse incoming customer messages to extract any order IDs mentioned, and inject them into the conversation context before passing to Claude.
• D.Add server-side validation that checks whether the order_id exists in your database before executing the refund, returning an error to the agent if not found.

Comment: *

Name: *

Email: *

Verification: *