Quiz — Session 5: Tools & Tool Calling

Program : Applied AI — Intermediate Level — Instructor: Yann Isola Format: 10 MCQs (multiple choice questionnaire) — only one correct answer per question — recommended duration: 8 minutes.

Question 1 — What is the fundamental difference between RAG (Retrieval-Augmented Generation) and tools?

HAS RAG is faster than tools B The RAG allows the model to read documents; the tools allow it to act and read living systems (databases, API, calendars) C Tools replace RAG in modern systems D RAG works offline, tools require Internet

Question 2 — When a model “calls a tool,” what actually happens?

HAS The model directly executes the tool code on the server B The model connects to the relevant API with its own credentials C The model issues a structured query (block tool_use ) ; it's your code that executes the actual call with your permissions, validation, and logging D The model provider (Anthropic, OpenAI, etc.) executes the call in its cloud

Question 3 — Why do we say that “tool descriptions are prompts”?

HAS Because they must be written in English B Because the model chooses which tool to use by reading the descriptions: a vague description causes bad routing C Because they replace the system message D Because they are billed at the same rate as prompts

Question 4 — What are the three elements of a tool definition?

HAS name , description , input_schema (in JSON Schema format) B url , api_key , timeout C nom , code_source , permissions D prompt , temperature , max_tokens

Question 5 — What does the parameter do? `tool_choice: "any"` ?

HAS It leaves the model free to use a tool or respond directly B It forces the model to use a specific tool, designated by its name C It forces the model to use at least one of the available tools (useful for structured extraction), without imposing which one D It disables all tools

Question 6 — In the tool_use loop, what is the field used for? `tool_use_id` of the block `tool_result` ?

HAS To authenticate the user to the API B To match each result with the corresponding tool request — essential especially when the model requires several tools in parallel C To encrypt the content of the result D Indicate the version of the tool used

Question 7 — The Weather API is down. What is the RIGHT way to report this to the model?

HAS Resend "OK" so as not to disrupt the conversation B Do not return anything and cut off the conversation C Resend a tool_result with is_error: true and a descriptive message, so that the model can correct itself or honestly inform the user (graceful degradation) D Retry silently indefinitely until the API responds

Question 8 — What is the risk of returning `"OK"` to the model when the tool has failed?

HAS Nothing, the model automatically detects faults B A JSON syntax error C The model, believing it has a valid result, risks inventing a plausible answer: a hallucination caused by your code D The conversation is automatically interrupted by the API

Question 9 — A consultation agent must only READ client files. According to the principle of least privilege, what tools do you expose to him?

HAS chercher_client only (read only, restricted scope) B chercher_client + modifier_client + supprimer_client , “just in case” C A generic tool executer_sql which accepts any SQL (Structured Query Language) query D All the company's tools, to maximize your autonomy

Question 10 — Among these tool definitions, which one respects good practices (“a tool does one thing, clear name, documented borderline cases”)?

HAS name: "outil1", description: "Fait des trucs avec les données." B name: "gestion", description: "Gère la météo, les clients, les calculs et les e-mails." C name: "obtenir_meteo",

description: "Obtient la météo actuelle pour une ville donnée. Ne pas utiliser pour des moyennes historiques. Retourne température en Celsius et conditions. Si la ville est ambiguë, préciser le pays."

D name: "obtenir_meteo", description: "Météo. Clé API : sk-prod-42abc."