Tool: get_document
Use this tool to retrieve the full content of a single document. The document name should be obtained from the parent field of results from a call to the search_documents tool. If you need to retrieve multiple documents, use batch_get_documents instead.
The following sample demonstrate how to use curl to invoke the get_document MCP tool.
| Curl Request |
|---|
curl --location 'https://developerknowledge.googleapis.com' \ --header 'content-type: application/json' \ --header 'accept: application/json, text/event-stream' \ --data '{ "method": "tools/call", "params": { "name": "get_document", "arguments": { // provide these details according to the tool's MCP specification } }, "jsonrpc": "2.0", "id": 1 }' |
Input Schema
Request schema for get_document.
GetDocumentRequest
| JSON representation |
|---|
{ "name": string } |
| Fields | |
|---|---|
name |
Required. The name of the document to retrieve. Format: |
Output Schema
A Document represents a piece of content from the Developer Knowledge corpus.
Document
| JSON representation |
|---|
{ "name": string, "uri": string, "content": string, "description": string } |
| Fields | |
|---|---|
name |
Identifier. The resource name of the document. Format: |
uri |
Output only. The URI of the content, such as |
content |
Output only. The content of the document in Markdown format. If this document is returned by search_documents, this field contains a snippet of text relevant to the search query. If this document is returned by get_document or batch_get_documents, this field contains the full document content. |
description |
Output only. A description of the document. |
Tool Annotations
Destructive Hint: ❌ | Idempotent Hint: ✅ | Read Only Hint: ✅ | Open World Hint: ❌