Descripciones de campos que orientan al modelo

Each field's name and description are shown to the AI. A good description is your chance to tell the model exactly what to put there.

Pass description to Field to attach a human sentence that travels with the schema all the way to the client.

Concrete examples inside a description, like a sample date or format, guide the model far better than abstract wording.

If a number has units, say so. Telling the model temperature is in Celsius prevents quietly wrong Fahrenheit values.

A field called id is vague. A description like the order's unique ID removes guesswork about which id you mean.

When a string follows a shape, describe it. Saying phone in E.164 like plus and digits keeps the format consistent.

For optional fields, mention when to skip them. Telling the model leave blank to use the default reduces needless values.

One clear sentence beats a paragraph. A focused description is easier for the model to follow and cheaper in tokens.

A short docstring on the model class describes the whole input, giving the AI useful context above the individual fields.

Every description lands in the JSON schema the client sends to the model, so writing them well directly shapes tool calls.

If the model keeps filling a field wrong, the fix is usually the description: sharpen the words until calls come out right.

Where does a Field description end up, and why does it matter?

Write tight field descriptions with examples, units, and formats. They reach the model in the schema and steer it toward correct calls. ✅