Jan 30, 2026

Tool schemas are now cleaner for optional fields by removing redundant anyOf: [{type}, {type: "null"}] constructs.

Background: How JSON Schema Handles Optional Fields

In JSON Schema, there are two distinct concepts:

Previously, our schemas used anyOf with null type for all optional fields—even when the field wasn't in required. This was redundant: if a field can be omitted, explicitly marking it as "accepts null" adds no value.

What Changed

For fields that are not in the required array, the schema processing now:

• Removes the redundant {type: "null"} from anyOf arrays
• Removes default: null since it's implied by being optional
• Flattens single-type anyOf to direct type declarations

Before vs After

For example, the page_token field in GOOGLECALENDAR_LIST_CALENDARS (which is optional/not required):

Previous (verbose):

{
  "page_token": {
    "anyOf": [
      { "type": "string" },
      { "type": "null" }
    ],
    "default": null,
    "description": "Token for the page of results to return...",
    "title": "Page Token"
  }
}

Now (simplified):

{
  "page_token": {
    "type": "string",
    "description": "Token for the page of results to return...",
    "title": "Page Token"
  }
}

What's Preserved

• Required nullable fields: Fields in the required array that accept null still use anyOf with null type
• Union types: Fields accepting multiple value types (e.g., string | number) retain their full anyOf array

Why This Matters

• Fewer tokens: Simpler schemas reduce token usage when tools are passed to LLMs
• Better compatibility: Some code generators and validators handle direct types better than anyOf constructs
• Clearer semantics: Non-required fields don't need explicit null type—being optional already implies they can be omitted