Define the tool registry runtime input contract

The accepted input remains: tool name, JSON args, registry of handlers. Keep parsing and normalization in functions that do not score, train, or call a model. That split lets a test fail the boundary without blaming the core logic. The user-facing decision stays: route model tool requests through a registry that validates names and args.

const registry=new Map([['calc', (a,b)=>a+b],['kb.lookup', id=>({id, text:'fixture'})]]);
if(!registry.has('calc')) throw new Error('missing calc');
console.log([...registry.keys()]);

Expected evidence: registry keys. If the contract is silent on a bad value, later debugging will look like an algorithm bug when it is really a data bug.

Write one assertion for a neighboring valid input to the tool registry runtime so tightening the boundary does not over-reject. Document field names and types the way a teammate would need them on day two of tools-in-code—not as comments you plan to delete.

List every field in registry with calc and kb.lookup and mark each as required, optional, or forbidden. Required fields must fail loudly when missing; optional fields need defaults you can quote in a test; forbidden fields (secrets, raw PII, path escapes) must never be accepted silently. This list is the contract for the tool registry runtime.

Add one sentence about encoding, units, or timezones if relevant to tool name, JSON args, registry of handlers. Contracts that ignore units create “correct” programs that still ship wrong decisions when someone tries to route model tool requests through a registry that validates names and args.

Write the error string you want for the most likely bad input. Prefer ValueError('threshold out of range')-style messages over generic invalid input. The contract’s job is to make string-eval calculator, or lookup that returns entire DB on missing id harder to confuse with a model or algorithm bug later.

At the data contract stage for tools-in-code, the job is narrower than finishing a product demo. You are creating one progressive evidence piece about registry with calc and kb.lookup that later pages inherit without redefining success. Keep that fixture small enough to inspect by hand, keep outputs copy-pasteable as text, and refuse to narrate this baseline as if it were a production SLA: inline if/else tool routing without schemas.

For this page specifically, success looks like malformed inputs rejected with field-named errors while still centering the user decision to route model tool requests through a registry that validates names and args. If you cannot point to a file, command, or assertion that proves that for the tool registry runtime, stay on this page instead of advancing.

Glossary: tool · Glossary: structured output · Cheatsheet: production ops signals

Previous · Next