ToolDef class for dynamically creating tool definitions

[jjallaire-aisi]

This PR introduces a ToolDef class for creating tools dynamically.

Previously, tools could only defined using @tool decorators and documentation comments. It's now possible to create a tool dynamically from any function by creating a ToolDef. For example:

from inspect_ai.solver import use_tools
from inspect_ai.tool import ToolDef

async def addition(x: int, y: int):
    return x + y

add_tool = ToolDef(
    tool=addition,
    name="add",
    description="A tool to add numbers", 
    parameters={
        "x": "the x argument",
        "y": "the y argument"
    })
)

use_tools([add_tool])

This is effectively what happens under the hood when you use the @tool decorator. There is one critical requirement for functions that are bound to tools using ToolDef: type annotations must be provided in the function signature (e.g. x: int, y: int).

ToolDef can generally be used anywhere that Tool can be used (use_tools(), setting state.tools, etc.)