# mirascope.core.openai.tool
## <ApiType type="Module" path="core/openai/tool" symbolName="tool" /> tool
The `OpenAITool` class for easy tool usage with OpenAI LLM calls.
<Info title="Usage">
[Tools](/docs/v1/learn/tools)
</Info>
## <ApiType type="Class" path="core/openai/tool" symbolName="GenerateOpenAIStrictToolJsonSchema" /> GenerateOpenAIStrictToolJsonSchema
**Bases:**
<TypeLink type={{"type_str": "GenerateJsonSchemaNoTitles", "description": null, "kind": "simple", "doc_url": "/docs/v1/api/core/base/tool#generatejsonschemanotitles"}} />
## <ApiType type="Class" path="core/openai/tool" symbolName="OpenAIToolConfig" /> OpenAIToolConfig
A tool configuration for OpenAI-specific features.
**Bases:**
<TypeLink type={{"type_str": "ToolConfig", "description": null, "kind": "simple", "doc_url": "/docs/v1/api/core/base/tool#toolconfig"}} />
<AttributesTable
attributes={[
{
"name": "strict",
"type_info": {
"type_str": "bool",
"description": null,
"kind": "simple",
"doc_url": "https://docs.python.org/3/library/functions.html#bool"
}
}
]}
/>
## <ApiType type="Class" path="core/openai/tool" symbolName="OpenAITool" /> OpenAITool
A class for defining tools for OpenAI LLM calls.
Example:
```python
from mirascope.core import prompt_template
from mirascope.core.openai import openai_call
def format_book(title: str, author: str) -> str:
return f"{title} by {author}"
@openai_call("gpt-4o-mini", tools=[format_book])
def recommend_book(genre: str) -> str:
return f"Recommend a {genre} book"
response = recommend_book("fantasy")
if tool := response.tool: # returns an `OpenAITool` instance
print(tool.call())
```
**Bases:**
<TypeLink type={{"type_str": "BaseTool", "description": null, "kind": "simple", "doc_url": "/docs/v1/api/core/base/tool#basetool"}} />
<AttributesTable
attributes={[
{
"name": "tool_call",
"type_info": {
"type_str": "SkipJsonSchema[ChatCompletionMessageToolCall]",
"description": null,
"kind": "generic",
"base_type": {
"type_str": "SkipJsonSchema",
"description": null,
"kind": "simple",
"doc_url": "https://docs.pydantic.dev/latest/api/json_schema/#pydantic.json_schema.SkipJsonSchema"
},
"parameters": [
{
"type_str": "ChatCompletionMessageToolCall",
"description": null,
"kind": "simple",
"doc_identifier": "ChatCompletionMessageToolCall"
}
]
}
}
]}
/>
## <ApiType type="Function" path="core/openai/tool" symbolName="tool_schema" /> tool_schema
Constructs a JSON Schema tool schema from the `BaseModel` schema defined.
Example:
```python
from mirascope.core.openai import OpenAITool
def format_book(title: str, author: str) -> str:
return f"{title} by {author}"
tool_type = OpenAITool.type_from_fn(format_book)
print(tool_type.tool_schema()) # prints the OpenAI-specific tool schema
```
<ParametersTable
parameters={[
{
"name": "cls",
"type_info": {
"type_str": "Any",
"description": null,
"kind": "simple",
"doc_identifier": null
}
}
]}
/>
<ReturnTable
returnType={{
"type_info": {
"type_str": "ChatCompletionToolParam",
"description": null,
"kind": "simple",
"doc_identifier": "ChatCompletionToolParam"
}
}}
/>
## <ApiType type="Function" path="core/openai/tool" symbolName="from_tool_call" /> from_tool_call
Constructs an `OpenAITool` instance from a `tool_call`.
<ParametersTable
parameters={[
{
"name": "cls",
"type_info": {
"type_str": "Any",
"description": null,
"kind": "simple",
"doc_identifier": null
}
},
{
"name": "tool_call",
"type_info": {
"type_str": "ChatCompletionMessageToolCall",
"description": null,
"kind": "simple",
"doc_identifier": "ChatCompletionMessageToolCall"
},
"description": "The OpenAI tool call from which to construct this tool instance."
},
{
"name": "allow_partial",
"type_info": {
"type_str": "bool",
"description": null,
"kind": "simple",
"doc_url": "https://docs.python.org/3/library/functions.html#bool"
},
"default": "False",
"description": "Whether to allow partial JSON data."
}
]}
/>
<ReturnTable
returnType={{
"type_info": {
"type_str": "OpenAITool",
"description": null,
"kind": "simple",
"doc_url": "/docs/v1/api/core/openai/tool#openaitool"
}
}}
/>