Skip to main content
Glama

add_table_records_tool

Add new rows to Google Sheets tables while maintaining column structure and automatic formatting for consistent data entry.

Instructions

Add records (rows) into a table in Google Sheets at the end.

This tool adds new records into a table at the end using InsertRangeRequest,
UpdateCellsRequest, and UpdateTableRequest operations. Each record must match the table's column structure.
Records are automatically formatted according to column types.

Args:
    spreadsheet_name: Name of the spreadsheet
    sheet_name: Name of the sheet containing the table
    table_name: Name of the table to add records into
    records: List of records, where each record is a list of values matching table columns

Returns:
    JSON string with success status and operation details

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
spreadsheet_nameYesThe name of the Google Spreadsheet
sheet_nameYesThe name of the sheet containing the table
table_nameYesName of the table to add records into
recordsYesList of records to add into the table. Each record must be a list of values matching the table's column structure. Values can be strings, numbers, booleans, or None. EXAMPLE: [ ['John Doe', 30, 'HR', 50000], ['Jane Smith', 25, 'Engineering', 60000], ['Bob Johnson', 35, 'Marketing', 55000] ]

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • Core handler function executing the tool logic: validates records against table structure, performs batch Google Sheets API requests to insert new rows at table end, populate values with column-type formatting, and extends the table range to include new records.
    def add_table_records_handler(
        drive_service,
        sheets_service,
        spreadsheet_name: str,
        sheet_name: str,
        table_name: str,
        records: List[List[Union[str, int, float, bool, None]]]
    ) -> str:
        """
        Add records (rows) into a table in Google Sheets using InsertRangeRequest, UpdateCellsRequest, and UpdateTableRequest.
        
        According to the official Google Sheets API documentation, to add records into a table:
        1. Use InsertRangeRequest to insert new rows at the end of the table
        2. Use UpdateCellsRequest to write values into the inserted rows
        3. Use UpdateTableRequest to update the table's range to include the new rows
        4. Each record must match the table's column structure
        5. Values are automatically formatted based on column types
        
        Args:
            drive_service: Google Drive service instance
            sheets_service: Google Sheets service instance
            spreadsheet_name: Name of the spreadsheet
            sheet_name: Name of the sheet containing the table
            table_name: Name of the table to add records into
            records: List of records, where each record is a list of values matching table columns
        
        Returns:
            str: Success message with operation details or error message
        """
        try:
            # Validate inputs
            if not table_name or table_name.strip() == "":
                return compact_json_response({
                    "success": False,
                    "message": "Table name is required."
                })
            
            if not records or not isinstance(records, list):
                return compact_json_response({
                    "success": False,
                    "message": "Records are required and must be a list of record lists."
                })
            
            if len(records) == 0:
                return compact_json_response({
                    "success": False,
                    "message": "At least one record must be provided."
                })
            
            # Get spreadsheet ID
            spreadsheet_id = get_spreadsheet_id_by_name(drive_service, spreadsheet_name)
            if not spreadsheet_id:
                return compact_json_response({
                    "success": False,
                    "message": f"Spreadsheet '{spreadsheet_name}' not found."
                })
    
            # Get sheet ID
            sheet_ids = get_sheet_ids_by_names(sheets_service, spreadsheet_id, [sheet_name])
            sheet_id = sheet_ids.get(sheet_name)
            if sheet_id is None:
                return compact_json_response({
                    "success": False,
                    "message": f"Sheet '{sheet_name}' not found in spreadsheet '{spreadsheet_name}'."
                })
            
            # Get table ID
            table_ids = get_table_ids_by_names(sheets_service, spreadsheet_id, sheet_name, [table_name])
            table_id = table_ids.get(table_name)
            if not table_id:
                return compact_json_response({
                    "success": False,
                    "message": f"Table '{table_name}' not found in sheet '{sheet_name}'."
                })
            
            # Get table information
            try:
                table_info = get_table_info(sheets_service, spreadsheet_id, table_id)
                table_range = table_info.get('range', {})
                current_column_count = table_info.get('column_count', 0)
                columns = table_info.get('columns', [])
            except Exception as e:
                return compact_json_response({
                    "success": False,
                    "message": f"Could not retrieve information for table '{table_name}': {str(e)}"
                })
            
            if current_column_count == 0:
                return compact_json_response({
                    "success": False,
                    "message": f"Table '{table_name}' has no columns defined."
                })
            
            # Get table boundaries
            table_start_row = table_range.get("startRowIndex", 0)
            table_end_row = table_range.get("endRowIndex", 0)
            table_start_col = table_range.get("startColumnIndex", 0)
            table_end_col = table_range.get("endColumnIndex", 0)
            
            # Always insert at the end of the table
            insert_row_index = table_end_row
            
            # Validate and process each record
            validated_records = []
            for i, record in enumerate(records):
                if not isinstance(record, list):
                    return compact_json_response({
                        "success": False,
                        "message": f"Record {i + 1} must be a list of values."
                    })
                
                # Validate record data structure against table columns
                record_validation = validate_row_data(record, current_column_count)
                if not record_validation["valid"]:
                    return compact_json_response({
                        "success": False,
                        "message": f"Invalid record {i + 1}: {record_validation['error']}"
                    })
                
                validated_records.append(record_validation["cleaned_row"])
            
            # Create batch update requests
            requests = []
            
            # 1. InsertRangeRequest to insert rows
            insert_range_request = {
                "insertRange": {
                    "range": {
                        "sheetId": sheet_id,
                        "startRowIndex": insert_row_index,
                        "endRowIndex": insert_row_index + len(validated_records),
                        "startColumnIndex": table_start_col,
                        "endColumnIndex": table_end_col
                    },
                    "shiftDimension": "ROWS"
                }
            }
            requests.append(insert_range_request)
            
            # 2. UpdateCellsRequest to set values in the inserted rows
            rows_data = []
            for record in validated_records:
                row_values = []
                for i, cell_value in enumerate(record):
                    # Get column type for proper formatting
                    column_type = "TEXT"  # Default type
                    if i < len(columns):
                        column_type = columns[i].get("type", "TEXT")
                    
                    # Create cell data with proper formatting
                    cell_data = create_cell_with_formatting(cell_value, column_type)
                    row_values.append(cell_data)
                
                rows_data.append({"values": row_values})
            
            update_cells_request = {
                "updateCells": {
                    "range": {
                        "sheetId": sheet_id,
                        "startRowIndex": insert_row_index,
                        "endRowIndex": insert_row_index + len(validated_records),
                        "startColumnIndex": table_start_col,
                        "endColumnIndex": table_end_col
                    },
                    "rows": rows_data,
                    "fields": "*"
                }
            }
            requests.append(update_cells_request)
            
            # 3. UpdateTableRequest to update the table's range after inserting rows
            # Calculate new end row index: original end + number of inserted rows
            new_end_row_index = table_end_row + len(validated_records)
            
            update_table_request = {
                "updateTable": {
                    "table": {
                        "tableId": table_id,
                        "range": {
                            "sheetId": sheet_id,
                            "startRowIndex": table_start_row,
                            "endRowIndex": new_end_row_index,  # Extend table range to include new rows
                            "startColumnIndex": table_start_col,
                            "endColumnIndex": table_end_col
                        }
                    },
                    "fields": "range"
                }
            }
            requests.append(update_table_request)
            
            # Execute the batch update request
            response = sheets_service.spreadsheets().batchUpdate(
                spreadsheetId=spreadsheet_id,
                body={"requests": requests}
            ).execute()
            
            # Extract response information
            replies = response.get("replies", [])
            if replies and len(replies) >= 3:
                insert_result = replies[0].get("insertRange", {})
                update_result = replies[1].get("updatedCells", {})
                update_table_result = replies[2].get("updateTable", {})
                
                # Get updated table information
                try:
                    updated_table_info = get_table_info(sheets_service, spreadsheet_id, table_id)
                    updated_range = updated_table_info.get('range', {})
                    updated_row_count = updated_table_info.get('row_count', 0)
                except Exception:
                    updated_range = {}
                    updated_row_count = 0
                
                response_data = {
                    "success": True,
                    "spreadsheet_name": spreadsheet_name,
                    "sheet_name": sheet_name,
                    "table_name": table_name,
                    "records_inserted": len(validated_records),
                    "insert_row_index": insert_row_index,
                    "updated_range": updated_range,
                    "updated_row_count": updated_row_count,
                    "inserted_records": validated_records,
                    "message": f"Successfully inserted {len(validated_records)} record(s) into table '{table_name}' in '{sheet_name}' at the end"
                }
                
                return compact_json_response(response_data)
            else:
                return compact_json_response({
                    "success": False,
                    "message": "Failed to insert records - insufficient response data from API (expected 3 operations)"
                })
            
        except HttpError as error:
            return compact_json_response({
                "success": False,
                "message": f"Google Sheets API error: {str(error)}"
            })
        except Exception as e:
            return compact_json_response({
                "success": False,
                "message": f"Error inserting table records: {str(e)}"
            }) 
  • Pydantic input schema definition with Field descriptions and validation for the tool parameters, including detailed examples in docstrings.
    @mcp.tool()
    def add_table_records_tool(
        spreadsheet_name: str = Field(..., description="The name of the Google Spreadsheet"),
        sheet_name: str = Field(..., description="The name of the sheet containing the table"),
        table_name: str = Field(..., description="Name of the table to add records into"),
        records: List[List[Union[str, int, float, bool, None]]] = Field(..., description="""List of records to add into the table.
        
        Each record must be a list of values matching the table's column structure.
        Values can be strings, numbers, booleans, or None.
        
        EXAMPLE: [
            ['John Doe', 30, 'HR', 50000],
            ['Jane Smith', 25, 'Engineering', 60000],
            ['Bob Johnson', 35, 'Marketing', 55000]
        ]
        """)
    ) -> str:
        """
        Add records (rows) into a table in Google Sheets at the end.
        
        This tool adds new records into a table at the end using InsertRangeRequest,
        UpdateCellsRequest, and UpdateTableRequest operations. Each record must match the table's column structure.
        Records are automatically formatted according to column types.
        
        Args:
            spreadsheet_name: Name of the spreadsheet
            sheet_name: Name of the sheet containing the table
            table_name: Name of the table to add records into
            records: List of records, where each record is a list of values matching table columns
        
        Returns:
            JSON string with success status and operation details
        """
        sheets_service, drive_service = _get_google_services()
        return add_table_records_handler(drive_service, sheets_service, spreadsheet_name, sheet_name, table_name, records)
  • Registers the add_table_records_tool with the MCP server using the @mcp.tool() decorator, making it available for invocation.
    @mcp.tool()
    def add_table_records_tool(
        spreadsheet_name: str = Field(..., description="The name of the Google Spreadsheet"),
        sheet_name: str = Field(..., description="The name of the sheet containing the table"),
        table_name: str = Field(..., description="Name of the table to add records into"),
        records: List[List[Union[str, int, float, bool, None]]] = Field(..., description="""List of records to add into the table.
        
        Each record must be a list of values matching the table's column structure.
        Values can be strings, numbers, booleans, or None.
        
        EXAMPLE: [
            ['John Doe', 30, 'HR', 50000],
            ['Jane Smith', 25, 'Engineering', 60000],
            ['Bob Johnson', 35, 'Marketing', 55000]
        ]
        """)
    ) -> str:
        """
        Add records (rows) into a table in Google Sheets at the end.
        
        This tool adds new records into a table at the end using InsertRangeRequest,
        UpdateCellsRequest, and UpdateTableRequest operations. Each record must match the table's column structure.
        Records are automatically formatted according to column types.
        
        Args:
            spreadsheet_name: Name of the spreadsheet
            sheet_name: Name of the sheet containing the table
            table_name: Name of the table to add records into
            records: List of records, where each record is a list of values matching table columns
        
        Returns:
            JSON string with success status and operation details
        """
        sheets_service, drive_service = _get_google_services()
        return add_table_records_handler(drive_service, sheets_service, spreadsheet_name, sheet_name, table_name, records)
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses that the tool uses specific Google Sheets operations (InsertRangeRequest, UpdateCellsRequest, UpdateTableRequest) and that records are automatically formatted, which adds valuable context. However, it doesn't mention permissions needed, error handling, or rate limits, leaving gaps for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with a clear purpose statement, operational details, and separate sections for Args and Returns. It's front-loaded with the core functionality. Some sentences could be more concise, but overall it's efficient with zero wasted text.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (mutation with 4 parameters), no annotations, and the presence of an output schema, the description is reasonably complete. It explains the operation, parameter roles, and return format. The output schema means the description doesn't need to detail return values, but it could better address behavioral aspects like error cases.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds minimal value beyond the schema, briefly restating parameter purposes without providing additional syntax or format details. The baseline score of 3 is appropriate given the comprehensive schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Add records (rows) into a table'), the resource ('Google Sheets'), and the location ('at the end'). It distinguishes from sibling tools like 'delete_table_records_tool' or 'update_table_cells_by_range_tool' by focusing on insertion rather than deletion or modification.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage by specifying 'at the end' and matching column structure, but lacks explicit guidance on when to use this tool versus alternatives like 'update_table_cells_by_range_tool' for modifying existing records or 'create_table_tool' for creating new tables. No exclusions or prerequisites are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/henilcalagiya/google-sheets-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server