Back to AI/ML Overview
🔧 Knowledge Site · Tools for Agentic Software · Schemas, Execution, MCP

Tools EngineeringThe model proposes a call. Your code decides whether it runs.

A tool is a capability outside the model that an agent may ask for. The model only writes a request: a name and some arguments. Application code validates it, authorizes it, executes it and reports back. This site starts from one plain function and climbs, one idea at a time, to schemas, result contracts, the , safe execution, retries and tests, asking one question at each step: who is allowed to do what, and what happens when it fails?

🎯The problem

An underwriting agent can fetch a roof assessment, search the underwriting guidance and record a recommendation. The first two only read; the third changes what the underwriter sees. If all three look the same to the model and the code that runs them, a malformed argument, a timeout or a retry can write twice or write the wrong thing. Tools engineering separates what the model asks for from what the application is willing to do.

🔑The question every page asks
Who is allowed to do what, and what happens when it fails? Three tools of one synthetic insurance agent, from a Python function and a Java record to an , each with strict arguments, a result contract and a failure path.

🗺️What is inside

From function to

Arguments, return values and side effects; how a model asks for a tool and the loop that answers; JSON Schema, type hints, Pydantic and Java records.

Results, discovery and

Success, error and partial results; naming and progressive disclosure; hosts, clients and servers, transports and authorization, per the current revision.

Safe execution

Least privilege, parameter validation, idempotency and sandboxing, and why a write tool needs stronger authorization than a read tool.

Reliability and testing

Retries, timeouts, rate limits and circuit breakers; contract tests, fault injection and trace-based checks for every tool.

🖱️How to read it

  • New to : read in order. Each chapter starts in plain English with one tiny example.
  • Experienced: jump to schemas, , safety or the insurance lab. The rigorous part sits in folded blocks.
  • Thirteen interactive labs, among them a Python and a Java tool builder and a fault simulator, each with a plain table next to it.
  • The example is synthetic and its agent is a scripted stand-in. Results show how the mechanism works, not how good any model is.