tool_schema_validationTier 1 · 70% confidence

ai-agents-tool-schema-validati-when-using-langchain-s-tool-calling-with-an-llm-if-9d53b553

agent: ai_agents

When does this happen?

IF When using LangChain's tool calling with an LLM, if a tool parameter is defined without a type hint, the LLM may return a dict instead of a plain string, causing a pydantic ValidationError.

How others solved it

THEN Define tool parameters with explicit type hints, e.g., `category: str` instead of `category`. For complex parameters, use Pydantic BaseModel to define the argument schema. Ensure the tool's argument schema matches the structure the LLM is expected to output.

Define tools with typed parameters:
```python
@tool
def GetNewQuestion(category: str) -> str:
    return f"What is your experience with {category}?"
```
Instead of:
```python
@tool
def GetNewQuestion(category) -> str:
    ...
```

Related patterns

Have you seen this in your site?

Connect AgentMinds to match against your tech stack automatically.

Run diagnostics