Skip to main content
Glama
michaelneale

Goose App Maker MCP

by michaelneale

app_response

Return structured responses to web applications created with Goose App Maker MCP, providing string, list, or table data formats for app functionality.

Instructions

Use this to return a response to the app that has been requested.
Provide only one of string_data, list_data, or table_data.

Args:
    string_data: Optional string response
    list_data: Optional list of strings response
    table_data: Optional table response with columns and rows
                Format: {"columns": ["col1", "col2", ...], "rows": [["row1col1", "row1col2", ...], ...]}

Returns:
    True if the response was stored successfully, False otherwise

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
string_dataNo
list_dataNo
table_dataNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • main.py:616-665 (handler)
    The core handler function for the 'app_response' MCP tool. It validates input (ensuring exactly one of string_data, list_data, or table_data is provided), stores the data in a global app_response variable, sets response_ready flag, and notifies waiting threads for the web app's HTTP polling endpoint to retrieve it.
    def app_response(string_data: str = None, 
                    list_data: List[str] = None, 
                    table_data: Dict[str, List] = None) -> bool:
        """
        Use this to return a response to the app that has been requested.
        Provide only one of string_data, list_data, or table_data.
        
        Args:
            string_data: Optional string response
            list_data: Optional list of strings response
            table_data: Optional table response with columns and rows
                        Format: {"columns": ["col1", "col2", ...], "rows": [["row1col1", "row1col2", ...], ...]}
        
        Returns:
            True if the response was stored successfully, False otherwise
        """
        global app_response, response_lock, response_ready
        
        try:
            # Check that exactly one data type is provided
            provided_data = [d for d in [string_data, list_data, table_data] if d is not None]
            if len(provided_data) != 1:
                logger.error("Exactly one of string_data, list_data, or table_data must be provided")
                return False
            
            # Determine the type of data and store it
            if string_data is not None:
                data = string_data
            elif list_data is not None:
                data = list_data
            elif table_data is not None:
                # Validate table_data format
                if not isinstance(table_data, dict) or "columns" not in table_data or "rows" not in table_data:
                    logger.error("Table data must have 'columns' and 'rows' keys")
                    return False
                data = table_data
            
            # Store the response and notify waiting threads
            with response_lock:
                global app_response  # Declare global inside the function block
                app_response = data
                global response_ready  # Declare global inside the function block
                response_ready = True
                response_lock.notify_all()
            
            return True
        except Exception as e:
            logger.error(f"Error storing response: {e}")
            return False
  • main.py:616-616 (registration)
    The @mcp.tool() decorator registers the app_response function as an MCP tool.
    def app_response(string_data: str = None, 
  • The function signature and docstring define the input schema (string_data, list_data, table_data) and output (bool success), with validation logic inside.
                list_data: List[str] = None, 
                table_data: Dict[str, List] = None) -> bool:
    """
    Use this to return a response to the app that has been requested.
    Provide only one of string_data, list_data, or table_data.
    
    Args:
        string_data: Optional string response
        list_data: Optional list of strings response
        table_data: Optional table response with columns and rows
                    Format: {"columns": ["col1", "col2", ...], "rows": [["row1col1", "row1col2", ...], ...]}
    
    Returns:
        True if the response was stored successfully, False otherwise
    """
  • main.py:38-40 (helper)
    Global variables used by the app_response tool handler and the HTTP server's wait_for_response endpoint to communicate responses from the MCP server to the web app frontend.
    app_response = None
    response_lock = threading.Condition()
    response_ready = False
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 of behavioral disclosure. It describes the tool's behavior by specifying the return value ('True if the response was stored successfully, False otherwise') and the parameter constraints, but it lacks details on permissions, rate limits, or error handling. This is adequate for a basic tool but misses deeper behavioral traits.

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 appropriately sized and front-loaded, starting with the purpose and key usage rule. Sentences are efficient, with no wasted words. However, the structure could be slightly improved by separating the 'Args' and 'Returns' sections more clearly, but overall it's concise and well-organized.

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 complexity (3 parameters, nested objects, no annotations, but has an output schema), the description is fairly complete. It covers purpose, parameter semantics, and return values, and the output schema handles return details, so no need to explain those further. It could benefit from more behavioral context, but it's sufficient for basic use.

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

Parameters5/5

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

The description adds significant meaning beyond the input schema, which has 0% description coverage. It explains the semantics of each parameter (string_data, list_data, table_data), provides a format example for table_data, and clarifies that only one should be provided. This fully compensates for the schema's lack of descriptions, making parameters clear and actionable.

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

Purpose4/5

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

The description clearly states the tool's purpose: 'to return a response to the app that has been requested.' It specifies the verb ('return a response') and resource ('to the app'), making it understandable. However, it doesn't explicitly differentiate from siblings like app_error or app_list, which might also involve app interactions, so it misses full sibling distinction.

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 provides implied usage guidance: 'Provide only one of string_data, list_data, or table_data,' indicating mutual exclusivity among parameters. It doesn't explicitly state when to use this tool versus alternatives like app_error for errors or app_list for listing, nor does it mention prerequisites or exclusions, leaving usage context somewhat vague.

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/michaelneale/goose-app-maker-mcp'

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