The type of the tool input schema. Usually you don't need to specify this.
The TypeScript type representing the structure of the tool arguments generated by the LLM. Useful for type checking tool handler functions when using JSONSchema.
A description of the tool.
The name of the tool.
Whether to return the tool's output directly.
Setting this to true means that after the tool is called, an agent should stop looping.
A Zod schema representing the parameters of the tool.
Optional
options: Partial<RunnableConfig<Record<string, any>>> | Partial<RunnableConfig<Record<string, any>>>[]Optional
batchOptions: RunnableBatchOptions & { Optional
options: Partial<RunnableConfig<Record<string, any>>> | Partial<RunnableConfig<Record<string, any>>>[]Optional
batchOptions: RunnableBatchOptions & { Optional
options: Partial<RunnableConfig<Record<string, any>>> | Partial<RunnableConfig<Record<string, any>>>[]Optional
batchOptions: RunnableBatchOptionsThe input argument for the tool.
Optional
configArg: Callbacks | RunnableConfig<Record<string, any>>Optional configuration or callbacks for the tool.
Optional
tags: string[]Optional tags for the tool.
A Promise that resolves with a string.
Optional
options: Partial<RunnableConfig<Record<string, any>>>Optional
options: Partial<RunnableConfig<Record<string, any>>>
Interface that defines the shape of a LangChain structured tool.
A structured tool is a tool that uses a schema to define the structure of the arguments that the LLM generates as part of its ToolCall.