CCAR-F - Tool Design & MCP Integration - Section 2.3

Distribute tools appropriately across agents and configure tool choice.

Handing one agent too many tools degrades selection reliability by inflating decision complexity, and agents holding tools outside their specialisation tend to misuse them. Candidates should scope each subagent's tool set to its role, add narrow cross-role tools only for high-frequency needs, replace a generic tool with a constrained alternative, and configure tool_choice: auto, any, or a forced named tool to guarantee a call or fix the order of a pipeline.

scoped tool accesstool count and selection reliabilitycross-specialisation misusetool_choice auto, any, and forced selectionconstrained tool alternatives

Practice question for this objective

Free sampleTool Design & MCP Integrationmedium

A consumer business runs a Customer Support Resolution Agent on the Claude Agent SDK. Over eighteen months the single coordinator session has accumulated thirty-four tools: the four support tools get_customer, lookup_order, process_refund and escalate_to_human, plus inventory, logistics and analytics tools mounted from three further MCP servers. A review of 600 transcripts shows the agent picking a tool that cannot answer the customer's question in 11 percent of turns, most often reaching for a logistics shipment tool when the customer is disputing a charge. First-contact resolution has fallen to 68 percent against a target of 80 percent. Which change most effectively addresses the reviewed behaviour?

  • AKeep every tool mounted on the coordinator and add a numbered decision table to the system prompt describing which of the thirty-four tools applies to each category of customer request.
  • BSplit the work into specialist subagents, each defined with a scoped allowedTools list holding the few tools its task needs, and have the coordinator delegate to them through the Task tool. Correct
  • CSet tool_choice to any on every request so the coordinator is obliged to call a tool rather than answering from its own memory, and log each selection for weekly review.
  • DPaste the full documentation for all three mounted MCP servers into the project CLAUDE.md so that every tool description is available in context at the moment of selection.
Selection accuracy falls as tool count rises, so distribute tools across specialist subagents with scoped access instead of documenting a crowded set. The model chooses from whatever tool set is presented on the request, and reliability degrades as that set grows and as descriptions overlap. Partitioning the tools across subagents, each with a scoped allowedTools list, means the wrong tool is absent from the specialist's set rather than merely discouraged by prose, which converts a probabilistic error rate into a structural constraint.

Why A is wrong: Documenting the mapping is reasonable practice and may shave a few points off the error rate, but it leaves all thirty-four tools competing for attention on every request. It buys probabilistic compliance where reducing the candidate set gives a structural improvement.

Why B is correct: Selection reliability degrades as the candidate set grows, so the durable fix is to shrink the set each agent chooses from. Scoping allowedTools per AgentDefinition means a billing specialist is never offered a shipment tool, which removes the observed error rather than discouraging it.

Why C is wrong: Forcing a call is tempting because it sounds like tighter control of tool use, but the logged fault is choosing the wrong tool, not failing to call one. Obliging a call from the same crowded set leaves the misselection untouched and stops the agent replying in prose when that is correct.

Why D is wrong: Richer descriptions do help a thin tool definition, but these definitions are not thin and the volume added here dilutes attention further. Treating a larger context as a cure for attention spread across thirty-four similar tools makes the selection problem worse.

See more CCAR-F practice questions, answers explained.

More in this domain

Back to all Tool Design & MCP Integration objectives, or the CCAR-F cert hub.

Examworthy is not affiliated with or endorsed by Anthropic. Original, blueprint-aligned practice material only.