Agent.Tools

Tool Methods

Methods for discovering, executing, and managing tools in the xpander SDK.

get_tools() / getTools()

Returns available tools, optionally formatted for a specific LLM provider.

tools = agent.get_tools(llm_provider=LLMProvider.OPEN_AI)

Parameter	Type	Required	Description
`llm_provider`	LLMProvider enum	No	Format tools for a specific provider

Returns: Array of tool objects formatted for the specified LLM provider.

Different LLM providers require specific tool formats. Always specify the appropriate provider:

LLMProvider.OPEN_AI: For OpenAI models (GPT-3.5, GPT-4, GPT-4o)
LLMProvider.ANTHROPIC: For Anthropic Claude models directly
LLMProvider.GENERIC: Generic provider format
LLMProvider.BEDROCK_CLAUDE: Amazon Bedrock Claude models
LLMProvider.VERTEX_AI: Google Vertex AI models
LLMProvider.FRIENDLI_AI: For Claude models via FriendliAI API
LLMProvider.GEMINI_OPEN_AI: For Google Gemini with OpenAI format

run_tool() / runTool()

Executes a single tool by name with specified input parameters.

result = agent.run_tool(
    tool_name="web_search",
    tool_input={"query": "latest AI advancements"}
)

Parameter	Type	Required	Description
`tool_name`	string	Yes	Name of the tool to execute
`tool_input`	object	Yes	Input parameters for the tool

Returns: ToolCallResult object containing the execution result.

run_tools() / runTools()

Executes multiple tool calls extracted from an LLM response.

results = agent.run_tools(tool_calls=tool_calls)

Parameter	Type	Required	Description
`tool_calls`	array of ToolCall	Yes	Array of tool calls to execute

Returns: Array of ToolCallResult objects containing execution results.

add_tool_call_results() / addToolCallResults()

Adds tool execution results to the agent’s message history as tool messages.

from xpander_sdk import ToolCallResult

tool_results = [
    ToolCallResult(
        function_name="get_weather",
        tool_call_id="call-123",
        is_success=True,
        result="The weather in New York is sunny with a temperature of 72°F.",
        payload={"location": "New York"}
    )
]

agent.add_tool_call_results(tool_call_results=tool_results)

Parameter	Type	Required	Description
`tool_call_results`	List[ToolCallResult]	Yes	Array of tool results

Returns: void

This method is primarily needed for local tools whose results aren’t automatically reported to the platform. Cloud-based tools managed by the xpander.ai platform automatically add their results to the message history.

add_local_tools() / addLocalTools()

Adds custom, locally-implemented tools to the agent.

agent.add_local_tools([{
    "name": "tool_name",
    "description": "Tool description",
    "function": function_reference,
    "parameters": {
        "type": "object",
        "properties": {
            "param1": {
                "type": "string",
                "description": "Parameter description"
            }
        },
        "required": ["param1"]
    }
}])

Parameter	Type	Required	Description
`tools`	array of objects	Yes	Array of tool definitions to add

Returns: void

Tool Definition Object Properties

Property	Type	Required	Description
`name`	string	Yes	Unique name for the tool
`description`	string	Yes	Description of what the tool does
`function`	function	Yes	Reference to implementation function
`parameters`	object	Yes	JSON Schema of function parameters

Static Utility Methods

XpanderClient.format_tools() / formatTools()

Static utility method to format tools for various LLM providers.

from xpander_sdk import XpanderClient, LLMProvider

tools_formatted = XpanderClient.format_tools(
    tools=[
        {
            "name": "search",
            "description": "Search for information",
            "parameters": {
                "type": "object",
                "properties": {
                    "query": {
                        "type": "string",
                        "description": "The search query"
                    }
                },
                "required": ["query"]
            }
        }
    ],
    llm_provider=LLMProvider.OPEN_AI
)

Parameters

Parameter	Type	Required	Description
`tools`	array	Yes	Array of tool definitions
`llm_provider` / `llmProvider`	LLMProvider	Yes	Enum value representing the LLM provider

Returns

Returns tools formatted for the specified LLM provider.

XpanderClient.extract_tool_calls() / extractToolCalls()

Static utility for extracting tool calls from LLM responses.

from xpander_sdk import XpanderClient, LLMProvider
from openai import OpenAI

# Initialize OpenAI client
openai_client = OpenAI(api_key="your-openai-api-key")

# Get a response from OpenAI with tool calls
response = openai_client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Search for information about AI safety"}],
    tools=[{
        "type": "function",
        "function": {
            "name": "web_search",
            "description": "Search the web for information",
            "parameters": {
                "type": "object",
                "properties": {
                    "query": {
                        "type": "string",
                        "description": "The search query"
                    }
                },
                "required": ["query"]
            }
        }
    }],
    tool_choice="auto"
)

# Extract tool calls
tool_calls = XpanderClient.extract_tool_calls(
    llm_response=response.model_dump(),
    llm_provider=LLMProvider.OPEN_AI
)

print(f"Extracted {len(tool_calls)} tool calls")
for tc in tool_calls:
    print(f"Tool: {tc.name}")
    print(f"Payload: {tc.payload}")
    print(f"Type: {tc.type}")

Parameter	Type	Required	Description
`llm_response`	object	Yes	Raw response from the LLM
`llm_provider`	LLMProvider	Yes	Provider that generated the LLM response

Returns: Array of ToolCall objects extracted from the LLM response.

Always use the same provider for extracting tool calls as you used for retrieving tools. The provider must match the LLM that generated the response.

XpanderClient.retrieve_pending_local_tool_calls() / retrievePendingLocalToolCalls()

Filters tool calls to retrieve only those that should be processed locally.

local_tool_calls = XpanderClient.retrieve_pending_local_tool_calls(
    tool_calls=tool_calls
)

Parameter	Type	Required	Description
`tool_calls`	array of ToolCall	Yes	Array of tool calls to filter

Returns: Array of ToolCall objects that should be processed locally.

Agentic Interface Methods

retrieve_agentic_interfaces() / retrieveAgenticInterfaces()

Returns available connector interfaces that provide pre-built operations.

interfaces = agent.retrieve_agentic_interfaces()

Returns: Array of AgenticInterface objects representing available connectors.

retrieve_agentic_operations() / retrieveAgenticOperations()

Retrieves available operations from a specific interface.

operations = agent.retrieve_agentic_operations(agentic_interface=interface)

Parameter	Type	Required	Description
`agentic_interface`	AgenticInterface	Yes	The interface to get operations from

Returns: Array of Operation objects available from the specified interface.

attach_operations() / attachOperations()

Attaches operations to the agent so they become available as tools.

agent.attach_operations(operations=[operation1, operation2])

Parameter	Type	Required	Description
`operations`	array of Operation	Yes	Array of operations to attach

Returns: void

Type Definitions

ToolCall

Represents a tool call extracted from an LLM response.

interface ToolCall {
  id: string;
  name: string;
  type: ToolCallType;
  payload: any;
  graphApproved: boolean;
}

ToolCallResult

Represents the result of executing a tool call.

interface ToolCallResult {
  toolCallId: string;
  functionName: string;
  isSuccess: boolean;
  result: string;
  payload: any;
  graphApproved: boolean;
}

AgenticInterface

Represents a connector interface that provides operations.

interface AgenticInterface {
  id: string;
  name: string;
  description: string;
  iconUrl: string;
}

Operation

Represents a pre-built operation from an interface.

interface Operation {
  id: string;
  name: string;
  description: string;
  interface: AgenticInterface;
  parameters: object;
}

Usage Example

# Getting and executing tools
tools = agent.get_tools(llm_provider=LLMProvider.OPEN_AI)

# Extract tool calls from LLM response
tool_calls = XpanderClient.extract_tool_calls(
    llm_response=response,
    llm_provider=LLMProvider.OPEN_AI
)

# Execute the tools
results = agent.run_tools(tool_calls=tool_calls)

# Working with operations
interfaces = agent.retrieve_agentic_interfaces()
github_interface = next((i for i in interfaces if "github" in i.name.lower()), None)

if github_interface:
    operations = agent.retrieve_agentic_operations(agentic_interface=github_interface)
    agent.attach_operations(operations=[operations[0]])

Agent

Core agent functionality

Agent.Messages

Working with agent messages

Tasks

Managing agent tasks

XpanderClient

Main client for the xpander.ai SDK

Getting Started

xpander-sdk

Tool Methods

get_tools() / getTools()

run_tool() / runTool()

run_tools() / runTools()

add_tool_call_results() / addToolCallResults()

add_local_tools() / addLocalTools()

Tool Definition Object Properties

Static Utility Methods

XpanderClient.format_tools() / formatTools()

Parameters

Returns

XpanderClient.extract_tool_calls() / extractToolCalls()

XpanderClient.retrieve_pending_local_tool_calls() / retrievePendingLocalToolCalls()

Agentic Interface Methods

retrieve_agentic_interfaces() / retrieveAgenticInterfaces()

retrieve_agentic_operations() / retrieveAgenticOperations()

attach_operations() / attachOperations()

Type Definitions

ToolCall

ToolCallResult

AgenticInterface

Operation

Usage Example

Agent

Agent.Messages

Tasks

XpanderClient

Getting Started

xpander-sdk

​Tool Methods

​get_tools() / getTools()

​run_tool() / runTool()

​run_tools() / runTools()

​add_tool_call_results() / addToolCallResults()

​add_local_tools() / addLocalTools()

​Tool Definition Object Properties

​Static Utility Methods

​XpanderClient.format_tools() / formatTools()

​Parameters

​Returns

​XpanderClient.extract_tool_calls() / extractToolCalls()

​XpanderClient.retrieve_pending_local_tool_calls() / retrievePendingLocalToolCalls()

​Agentic Interface Methods

​retrieve_agentic_interfaces() / retrieveAgenticInterfaces()

​retrieve_agentic_operations() / retrieveAgenticOperations()

​attach_operations() / attachOperations()

​Type Definitions

​ToolCall

​ToolCallResult

​AgenticInterface

​Operation

​Usage Example

​Related Documentation

Agent

Agent.Messages

Tasks

XpanderClient

Tool Methods

get_tools() / getTools()

run_tool() / runTool()

run_tools() / runTools()

add_tool_call_results() / addToolCallResults()

add_local_tools() / addLocalTools()

Tool Definition Object Properties

Static Utility Methods

XpanderClient.format_tools() / formatTools()

Parameters

Returns

XpanderClient.extract_tool_calls() / extractToolCalls()

XpanderClient.retrieve_pending_local_tool_calls() / retrievePendingLocalToolCalls()

Agentic Interface Methods

retrieve_agentic_interfaces() / retrieveAgenticInterfaces()

retrieve_agentic_operations() / retrieveAgenticOperations()

attach_operations() / attachOperations()

Type Definitions

ToolCall

ToolCallResult

AgenticInterface

Operation

Usage Example

Related Documentation