Fix tool forward args with defaults but no type hint

docs/source/conceptual_guides/intro_agents.md

@@ -112,4 +112,4 @@ This is illustrated on the figure below, taken from [Executable Code Actions Eli
 
 <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/code_vs_json_actions.png">
 
-This is why we put emphasis on proposing code agents, in this case python agents, which meant putting higher effort on building secure python interpreters.
+This is why we put emphasis on proposing code agents, in this case python agents, which meant building secure python interpreters.

docs/source/examples/text_to_sql.md

@@ -19,7 +19,7 @@ rendered properly in your Markdown viewer.
 
 In this tutorial, we’ll see how to implement an agent that leverages SQL using `smolagents`.
 
-> Let's start with the goldnen question: why not keep it simple and use a standard text-to-SQL pipeline?
+> Let's start with the golden question: why not keep it simple and use a standard text-to-SQL pipeline?
 
 A standard text-to-sql pipeline is brittle, since the generated SQL query can be incorrect. Even worse, the query could be incorrect, but not raise an error, instead giving some incorrect/useless outputs without raising an alarm.
 
@@ -27,7 +27,7 @@ A standard text-to-sql pipeline is brittle, since the generated SQL query can be
 
 Let’s build this agent! 💪
 
-### Setup text to SQL
+First, we setup the SQL environment:
 ```py
 from sqlalchemy import (
     create_engine,
@@ -73,7 +73,7 @@ for row in rows:
 
 Now let’s make our SQL table retrievable by a tool.
 
-The tool’s description attribute will be embedded in the LLM’s prompt by the agent system: it gives the LLM information about how to use the tool. So that is where we want to describe the SQL table.
+The tool’s description attribute will be embedded in the LLM’s prompt by the agent system: it gives the LLM information about how to use the tool. This is where we want to describe the SQL table.
 
 ```py
 inspector = inspect(engine)

pyproject.toml

@@ -19,6 +19,7 @@ dependencies = [
     "pandas>=2.2.3",
     "jinja2>=3.1.4",
     "pillow>=11.0.0",
+    "llama-cpp-python>=0.3.4",
     "markdownify>=0.14.1",
     "gradio>=5.8.0",
     "duckduckgo-search>=6.3.7",

src/smolagents/tools.py

@@ -117,6 +117,10 @@ def _convert_type_hints_to_json_schema(func: Callable) -> Dict:
             properties[param_name] = _parse_type_hint(param_type)
             if signature.parameters[param_name].default != inspect.Parameter.empty:
                 properties[param_name]["nullable"] = True
+    for param_name in signature.parameters.keys():
+        if signature.parameters[param_name].default != inspect.Parameter.empty:
+            if param_name not in properties: # this can happen if the param has no type hint but a default value
+                properties[param_name] = {"nullable": True}
     return properties
 
 AUTHORIZED_TYPES = [