CCARF Practice Question

Paper 5 · Question 9

D2 Tool Design & MCP Integration · Paper 5

[Scenario: Multi-agent Research System] In your system design, you gave the document analysis agent access to a general-purpose tool `fetch_url` so it could download documents by URL. Production logs show this agent now frequently downloads search engine results pages to perform ad hoc web search—behavior that should be routed through the web-search agent—causing inconsistent results. Which fix is most effective?

• A.Replace `fetch_url` with a `load_document` tool that validates that URLs point to document formats.
• B.Remove `fetch_url` from the document analysis agent and route all URL fetching through the coordinator to the web-search agent.
• C.Implement filtering that blocks `fetch_url` calls to known search engine domains while allowing other URLs.
• D.Add instructions to the document analysis agent prompt that `fetch_url` should only be used to download document URLs, not to search.

Show answer & explanations

Correct answer: A

A: Replacing a general-purpose tool with a document-specific tool that validates URLs against document formats fixes the root cause by constraining capability at the interface level. This follows the principle of least privilege, making undesired search behavior impossible rather than merely discouraged.

B: Sending every URL through web search blocks ordinary document downloads and adds a hop for a capability the document agent should keep, narrowly.

C: A blocklist of known search domains is incomplete, and fetch_url can still be used as a general fetcher.

D: A prompt rule not to search is advisory. The tool can still fetch a results page, so the model sometimes will.

Related Tool Design & MCP Integration questions

More: Paper 5 · All practice questions