Interface Tool

Tool details of a tool that the model may use to generate a response.

interface Tool {
    codeExecution?: ToolCodeExecution;
    computerUse?: ComputerUse;
    enterpriseWebSearch?: EnterpriseWebSearch;
    fileSearch?: FileSearch;
    functionDeclarations?: FunctionDeclaration[];
    googleMaps?: GoogleMaps;
    googleSearch?: GoogleSearch;
    googleSearchRetrieval?: GoogleSearchRetrieval;
    mcpServers?: McpServer[];
    parallelAiSearch?: ToolParallelAiSearch;
    retrieval?: Retrieval;
    urlContext?: UrlContext;
}

Properties

codeExecution? computerUse? enterpriseWebSearch? fileSearch? functionDeclarations? googleMaps? googleSearch? googleSearchRetrieval? mcpServers? parallelAiSearch? retrieval? urlContext?

Properties

OptionalcodeExecution

codeExecution?: ToolCodeExecution

Optional. CodeExecution tool type. Enables the model to execute code as part of generation.

OptionalcomputerUse

computerUse?: ComputerUse

Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations.

OptionalenterpriseWebSearch

enterpriseWebSearch?: EnterpriseWebSearch

Optional. Tool to support searching public web data, powered by Vertex AI Search and Sec4 compliance. This field is not supported in Gemini API.

OptionalfileSearch

fileSearch?: FileSearch

Optional. Tool to retrieve knowledge from the File Search Stores.

OptionalfunctionDeclarations

functionDeclarations?: FunctionDeclaration[]

Optional. Function tool type. One or more function declarations to be passed to the model along with the current user query. Model may decide to call a subset of these functions by populating FunctionCall in the response. User should provide a FunctionResponse for each function call in the next turn. Based on the function responses, Model will generate the final response back to the user. Maximum 512 function declarations can be provided.

OptionalgoogleMaps

googleMaps?: GoogleMaps

Optional. Tool that allows grounding the model's response with geospatial context related to the user's query.

OptionalgoogleSearch

googleSearch?: GoogleSearch

Enables the model to execute Google Search as part of generation.

OptionalgoogleSearchRetrieval

googleSearchRetrieval?: GoogleSearchRetrieval

Optional. Specialized retrieval tool that is powered by Google Search.

OptionalmcpServers

mcpServers?: McpServer[]

Optional. MCP Servers to connect to. This field is not supported in Vertex AI.

OptionalparallelAiSearch

parallelAiSearch?: ToolParallelAiSearch

Optional. If specified, Vertex AI will use Parallel.ai to search for information to answer user queries. The search results will be grounded on Parallel.ai and presented to the model for response generation. This field is not supported in Gemini API.

Optionalretrieval

retrieval?: Retrieval

Optional. Retrieval tool type. System will always execute the provided retrieval tool(s) to get external knowledge to answer the prompt. Retrieval results are presented to the model for generation. This field is not supported in Gemini API.

OptionalurlContext

urlContext?: UrlContext

Optional. Tool to support URL context retrieval.

Settings

On This Page

Properties