You are supporting a team whose Claude Code sessions consistently load 60 or more MCP tools from many servers, exhausting context budget before the session begins.Which adjustment most directly addresses this issue without removing capability?
Answer(s): A
Tool Search applies progressive discovery to a large tool catalog. Instead of inserting every MCP tool's complete JSON schema and description into the initial context, Claude receives limited discovery information and loads the full definitions only when a task requires them. This preserves the available context for instructions, repository content, conversation history, and tool results without removing the underlying capabilities.Anthropic's Claude Code documentation states that Tool Search keeps MCP context usage low by deferring tool definitions until Claude needs them. Only the tools actually selected enter the working context. Claude Code MCP Tool SearchAnthropic's advanced-tool-use guidance also describes conventional multi-server configurations consuming tens of thousands of tokens before work begins, while on-demand discovery substantially reduces that overhead. Advanced Tool UseOption B solves context pressure by destroying required functionality. Option C worsens the constraint by adding more prompt tokens. Option D expands the exact source of context bloat.The team should also improve server and tool descriptions so discovery returns the correct tools, monitor tool-selection quality, and keep frequently required foundational tools non-deferred only when evaluations justify the additional context cost.Study Guide references/topics: MCP scaling; Tool Search; progressive discovery; deferred schemas; context-budget management; tool-selection accuracy.
You are evaluating an evaluation set used to score a Claude-based hiring-support tool. The set is drawn from one geographic region and one tenure band.Which response is most appropriate?
Answer(s): B
The existing evaluation set does not represent the population or operating conditions the hiring-support system will encounter. Option B corrects this coverage defect by expanding geographic and tenure slices and requiring the system to be rescored before broader deployment.Aggregate performance on one narrow group can conceal substantial differences among regions, experience levels, job families, languages, and other relevant cohorts. The expanded dataset should therefore support disaggregated metrics, not merely one combined score. It should also include representative, edge, and adversarial cases, with labels and grading procedures reviewed for consistency and potential bias.Anthropic's evaluation guidance states that evaluations should mirror the real-world task distribution and include edge cases. Success criteria should also be relevant to the application's actual purpose and users. Define Success Criteria and Build EvaluationsOption A replaces one unrepresentative method with another. Option C deliberately narrows coverage further. Option D mistakes high performance on a restricted subset for evidence of generalization.Because hiring is a consequential domain, the organization should combine representative quantitative evaluation, subgroup analysis, expert review, monitoring, access controls, transparency, and meaningful human responsibility for final decisions.Study Guide references/topics: Dataset representativeness; evaluation slices; subgroup performance; bias detection; consequential-use governance; pre-release rescoring.
MULTIPLE CHOICEYou are compiling guardrail tactics for a customer-facing assistant.Which two tactics belong on the guardrail list?Each correct answer presents a complete solution.
Answer(s): C,D
Option C introduces a deterministic validation boundary between probabilistic model output and downstream execution. Structured validation can reject missing fields, invalid types, unauthorized actions, malformed arguments, and values outside approved enumerations before any tool or business process acts on the response. Anthropic recommends Structured Outputs when guaranteed schema conformance is required. Increase Output ConsistencyOption D implements defense in depth. Prompt-level instructions establish intended behavior, while runtime classifiers, content filters, policy engines, output validators, tool permissions, and human confirmation gates provide controls outside the model. Anthropic's guardrail guidance recommends combining safeguards rather than depending on one mechanism. Mitigate Jailbreaks and Prompt InjectionsOption A creates a bypass mechanism that adversaries may discover or imitate. Option B may alter output variability but is not a security boundary and cannot guarantee policy compliance. Option E places complete reliance on a system prompt, which remains vulnerable to ambiguity, conflicting inputs, model errors, and indirect prompt injection.Guardrails should be risk-based, independently enforceable where possible, observable, tested against adversarial cases, and proportional to the consequences of downstream actions.Study Guide references/topics: Layered guardrails; structured validation; runtime content checks; prompt injection; deterministic enforcement; defense in depth.
You are configuring tool permissions for a Claude-based assistant. The assistant's defined responsibilities require read access to a knowledge base and write access to a draft queue, and nothing else.Which scoping design best applies least privilege?
Least privilege means granting the exact capabilities required for the defined responsibility---no more and no less. Option B permits the assistant to read the approved knowledge base and write only to the draft queue. Enforcing the allow-list at the orchestration layer creates a deterministic authorization boundary outside the model's prompt and reasoning.The rule should also be role-specific so different users or operational roles receive only the tools and data scopes they require. The knowledge-base tool should remain read-only, while the draft-queue tool should be restricted to draft creation rather than external sending, approval, or production publication.Option A exposes every globally readable tool, creating unnecessary access to unrelated information. Option C relies on voluntary model behavior instead of enforceable authorization. A mistaken tool selection or successful prompt injection could therefore invoke an inappropriate capability. Option D minimizes permissions by eliminating the assistant's required functionality and is not a viable least-privilege implementation.Anthropic's permission guidance distinguishes allow, ask, and deny rules and confirms that these controls are enforced by Claude Code rather than by model instructions. Configure PermissionsStudy Guide references/topics: Least privilege; per-role authorization; orchestration-layer enforcement; capability scoping; read/write separation; tool allow-lists.
MULTIPLE CHOICEA senior architect is managing stakeholder expectations for a Claude-based reporting assistant midway through development. Stakeholders have escalating concerns about response latency.Which two actions most directly address stakeholder expectation alignment in this situation? (Select two.)
Answer(s): A,E
Expectation alignment begins with measured evidence. Option A gives stakeholders the median experience through p50 latency and the slower-tail experience through p95, then compares both with the agreed SLA. The measurements should reflect representative input sizes, concurrency, retrieval activity, tool calls, geographic routing, and cache conditions.If the target remains infeasible after reasonable optimization, Option E establishes the correct governance response. The architect should collaboratively revise the SLA, scope, cost envelope, model choice, or user-experience design rather than silently accepting a breach or making unilateral changes. Any revision should document the business impact and accepted trade-offs.Option B commits all resources before the problem's severity, causes, and business priority have been established. Option C wrongly treats latency as uncontrollable; model selection, prompt length, retrieval depth, caching, streaming, and architecture can materially affect it. Option D introduces an unvalidated provider and could create quality, security, compliance, and integration regressions.Expectation management is not merely communicating bad news. It requires transparent measurements, credible optimization options, explicit trade-offs, and jointly approved commitments that the production architecture can actually satisfy.Study Guide references/topics: SLA alignment; p50 and p95 latency; stakeholder negotiation; evidence-based communication; architectural trade-offs; production constraints.
Post your Comments and Discuss Anthropic CCAR-P exam prep with other Community members:
Our website is free, but we have to fight against AI bots and content theft. We're sorry for the inconvenience caused by these security measures. You can access the rest of the CCAR-P content, but please register or login to continue.