Quiz — Advanced Level, Session 2

“Advanced tool use”

Program : Applied AI — Yann Isola Format: 10 MCQs (Multiple Choice Questions), certification level Claude Certified Architect Recommended scale: 1 point per question, mastery threshold: 8/10 Duration : 20 mins

The commented corrections are at the end of the document.

Q1 — Life cycle

Your application receives a response from the Messages API with stop_reason: "tool_use". What does this field mean and what is the correct next step?

HAS The model ran a tool; you have to read the result in response.content . B The model requires the execution of one or more tools; your code must execute each block tool_use and return the tool_result in a message role: "user". C The model encountered a tool error; you must retry the request with the same messages. D The conversation is over; the assistant used an internal tool to produce its final response.

Q2 — Tool_result format

What message is valid to return a tool result to the Anthropic API?

HAS {"role": "tool", "content": [{"type": "tool_result", "tool_use_id": "toolu_01A", "content": "42"}]} B {"role": "user", "content": [{"type": "tool_result", "tool_use_id": "toolu_01A", "content": "42"}]} C {"role": "assistant", "content": [{"type": "tool_result", "tool_use_id": "toolu_01A", "content": "42"}]} D {"role": "user", "content": [{"type": "tool_output", "id": "toolu_01A", "content": "42"}]}

Q3 — Chat history

After receiving a block tool_use , a developer constructs the following query by only including: the initial user message + a user message with the tool_result . What is happening?

HAS The API accepts: tool_use_id is enough to make the connection. B The API accepts but the model ignores the result. C The API returns a 400 error: the wizard message containing the block tool_use corresponding must appear in the history. D The API returns a 429 error (rate limit).

Q4 — tool_choice

You build an intention router: each user message must be classified by ONE of the 5 routing tools available, depending on the model. What tool_choice is the most suitable?

HAS {"type": "auto"} B {"type": "any"} C {"type": "tool", "name": "route_intent"} D Omit tool_choice and require it in the system prompt.

Q5 — Structured output

What is the main advantage of the “false tool” pattern (tool never executed + tool_choice: {"type": "tool", ...}) compared to the instruction “reply only in JSON” in the prompt?

HAS It reduces latency because the model generates fewer tokens. B It semantically guarantees that the extracted values are exact. C It guarantees schema-compliant output (parsed JSON, constrained fields and types), eliminating spurious text and format errors. D It is less expensive because tool definitions do not consume input tokens.

Q6 — Taxonomy of errors

An extraction pipeline returns valid, schema-compliant JSON, but systematically categorizes “refund” tickets as technique instead of facturation . What is the nature of the error and the priority remedy?

HAS Syntax → retry the call with the same request. B Syntactic → increase max_tokens . C Semantics → refine the prompt: enrich the description of the tool and enum values, add examples. D Semantics → retry the call: the temperature will introduce corrective variability.

Q7 — is_error

Your tool get_invoice throws an “invoice not found” exception. What is the best practice?

HAS Break the loop and display the exception to the end user. B Resend a tool_result with is_error: true and an actionable message (e.g. “INV-123 invoice not found, check identifier”), then let the model decide what to do next. C Do not return anything for this tool_use and let the model try again spontaneously. D Return the complete stack trace in content so that the model has as much information as possible.

Q8 — Multi-tool

A model response contains two blocks tool_use (ids toolu_A And toolu_B ). What is the correct way to return results?

HAS Two messages role: "user" successive, one by tool_result . B A single message role: "user" containing the two blocks tool_result , each with their tool_use_id . C Only one tool_result concatenating the two outputs, with the id of the first block. D Execute only the first tool: the model will request the second one again the next turn.

Q9 — Security

Which of these statements correctly describes the tool use security model?

HAS The model runs the tools in a sandbox hosted by Anthropic, with the permissions declared in input_schema . B The model does not execute anything: the tools run in your code with your authentications; So input validation and access control are entirely up to your application. C The API validates the input against the schema and blocks any dangerous values (SQL injection, file paths) before passing them to you. D Provide enum in the schema is enough to guarantee that the values received are safe for an SQL query.

Q10 — max_tokens and tool_use

A response comes with stop_reason: "max_tokens" while the last block of content is a tool_use whose input seems incomplete. Which analysis is correct?

HAS It's impossible: a block tool_use is always issued in full or not at all. B Semantic error: the model misunderstood the schema; the description of the tool must be rewritten. C Syntactic error due to truncation: the JSON of the call has been cut; you have to restart with a max_tokens higher and check stop_reason before any analysis. D Normal behavior: the API will complete the input to the next request thanks to tool_use_id .