Attempting to use pydantic models as tool args causes `ParseError` in `ChatVertexAI`

Example Pydantic schema:

class IntOrFloat(BaseModel):
    """A type that can be either an int or a float."""

    number: int | float

and tool:

@tool
def add(a: IntOrFloat, b: IntOrFloat) -> IntOrFloat:
    """Adds a and b."""
    return IntOrFloat(number=a.number + b.number)

Attempting to use this tool in a tool-calling agent with ChatVertexAI causes the following error:

ParseError: Failed to parse properties field: Failed to parse properties field: Failed to parse anyOf field: Failed to parse type field: Invalid enum value integer for enum type google.cloud.aiplatform.v1beta1.Type at Schema.properties[a].properties[number].anyOf[0].type....