Skip to main content
Glama
ibm-ecm

Core Content Services MCP Server

Official
by ibm-ecm

delete_folder

Deletes a folder from the content repository using its unique identifier or path. Returns the folder ID on success.

Instructions

Deletes a folder in the content repository. This tool interfaces with the GraphQL API to delete a folder object with the provided id.

:param id_or_path string Yes The unique identifier or path for the folder. If not provided, an error will be returned.

:returns: If successful, return the folder id. Else, return a ToolError instance that describes the error.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
id_or_pathYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • The register_folder_tools function that registers all folder tools including delete_folder on the FastMCP server instance.
    def register_folder_tools(mcp: FastMCP, graphql_client: GraphQLClient) -> None:
        @mcp.tool(
            name="create_folder",
  • The delete_folder tool handler decorated with @mcp.tool(name='delete_folder'). Takes an id_or_path string, validates input, executes a GraphQL deleteFolder mutation, and returns the folder ID or a ToolError on failure.
    @mcp.tool(
        name="delete_folder",
    )
    def delete_folder(id_or_path: str) -> Union[str, ToolError]:
        """
        Deletes a folder in the content repository. This tool interfaces with the GraphQL API
        to delete a folder object with the provided id.
    
    
        :param id_or_path	string	Yes	The unique identifier or path for the folder. If not provided, an error will be returned.
    
        :returns: If successful, return the folder id.
         Else, return a ToolError instance that describes the error.
        """
        method_name = "delete_folder"
        try:
            # check id or path
            if not id_or_path:
                return ToolError(
                    message=f"delete_folder failed: id is a required input.",
                )
    
            mutation = """
                    mutation deleteFolder( $id_or_path:String!
                    $repo: String!)
                    {
                    deleteFolder(repositoryIdentifier: $repo, 
                        identifier: $id_or_path
                    )
                    {
                        id
                        className
                    }
                    }
            """
            var = {
                "repo": graphql_client.object_store,
                "id_or_path": id_or_path,
            }
            response = graphql_client.execute(query=mutation, variables=var)
            # handling exception, for example duplicate folder name
            if "errors" in response:
                return ToolError(
                    message=f"delete_folder failed: got err {response}.",
                )
    
            return response["data"]["deleteFolder"]["id"]
    
        except Exception as e:
            error_traceback = traceback.format_exc(limit=TRACEBACK_LIMIT)
            logger.error(
                f"{method_name} failed: {e.__class__.__name__} - {str(e)}\n{error_traceback}"
            )
    
            return ToolError(
                message=f"{method_name} failed: got err {e}. Trace available in server logs.",
            )
  • GraphQL mutation used by delete_folder to delete a folder via the deleteFolder mutation with repository and identifier arguments.
    mutation = """
            mutation deleteFolder( $id_or_path:String!
            $repo: String!)
            {
            deleteFolder(repositoryIdentifier: $repo, 
                identifier: $id_or_path
            )
            {
                id
                className
            }
            }
    """
  • Import of register_folder_tools from cs_mcp_server.tools.folders in the main server file.
    from cs_mcp_server.tools.folders import register_folder_tools
    from cs_mcp_server.tools.annotations import register_annotation_tools
    from cs_mcp_server.tools.property_extraction import register_property_extraction_tools
    from cs_mcp_server.tools.classification import register_classification_tools
  • Registration calls to register_folder_tools for both CORE and FULL server types.
    # Register tools based on server type
    if server_type == ServerType.CORE:
        register_document_tools(mcp, graphql_client, metadata_cache)
        register_folder_tools(mcp, graphql_client)
        register_class_tools(mcp, graphql_client, metadata_cache)
        register_search_tools(mcp, graphql_client, metadata_cache)
        # register_annotation_tools(mcp, graphql_client)
        # register_custom_object_tools(mcp, graphql_client)
        logger.info("Core tools registered")
    
    elif server_type == ServerType.AI__DOCUMENT_INSIGHT:
        register_advanced_search_tools(mcp, graphql_client, metadata_cache)
        register_vector_search_tool(mcp, graphql_client)
        logger.info("AI Document Insight tools registered")
    
    elif server_type == ServerType.LEGAL_HOLD:
        register_hold_tools(mcp, graphql_client)
        logger.info("Legal hold tools registered")
    
    elif server_type == ServerType.PROPERTY_EXTRACTION_AND_CLASSIFICATION:
        register_property_extraction_tools(mcp, graphql_client, metadata_cache)
        register_classification_tools(mcp, graphql_client, metadata_cache)
        logger.info("Property extraction and classification tools registered")
    
    elif server_type == ServerType.FULL:
        register_document_tools(mcp, graphql_client, metadata_cache)
        register_folder_tools(mcp, graphql_client)
        register_class_tools(mcp, graphql_client, metadata_cache)
        register_search_tools(mcp, graphql_client, metadata_cache)
        # register_annotation_tools(mcp, graphql_client)
        # register_custom_object_tools(mcp, graphql_client)
        register_vector_search_tool(mcp, graphql_client)
        register_advanced_search_tools(mcp, graphql_client, metadata_cache)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changedv1.0.4
    • addedInput schema / additionalProperties
      Added value: +false
    • removedInput schema / properties / id_or_path / title
      Removed value: -"Id Or Path"
    • removedInput schema / title
      Removed value: -"delete_folderArguments"
    • removedOutput schema / $defs
      Removed value: -{
      -  "ToolError": {
      -    "description": "Represents an error response from a tool execution.\n\nThis class helps the LLM understand error messages and provides suggestions\nfor potential resolutions.",
      -    "properties": {
      -      "isError": {
      -        "const": true,
      -        "default": true,
      -        "description": "Indicates that an error occurred during tool execution if value is True",
      -        "title": "Iserror",
      -        "type": "boolean"
      -      },
      -      "message": {
      -        "description": "Detailed error message",
      -        "title": "Message",
      -        "type": "string"
      -      },
      -      "suggestions": {
      -        "description": "List of suggestions for resolving the error",
      -        "items": {
      -          "type": "string"
      -        },
      -        "title": "Suggestions",
      -        "type": "array"
      -      }
      -    },
      -    "required": [
      -      "message"
      -    ],
      -    "title": "ToolError",
      -    "type": "object"
      -  }
      -}
    • changedOutput schema / properties / result / anyOf
      Previous value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "$ref": "#/$defs/ToolError"
      -  }
      -]New value: +[
      +  {
      +    "type": "string"
      +  },
      +  {
      +    "description": "Represents an error response from a tool execution.\n\nThis class helps the LLM understand error messages and provides suggestions\nfor potential resolutions.",
      +    "properties": {
      +      "isError": {
      +        "const": true,
      +        "default": true,
      +        "description": "Indicates that an error occurred during tool execution if value is True",
      +        "type": "boolean"
      +      },
      +      "message": {
      +        "description": "Detailed error message",
      +        "type": "string"
      +      },
      +      "suggestions": {
      +        "description": "List of suggestions for resolving the error",
      +        "items": {
      +          "type": "string"
      +        },
      +        "type": "array"
      +      }
      +    },
      +    "required": [
      +      "message"
      +    ],
      +    "type": "object"
      +  }
      +]
    • removedOutput schema / properties / result / title
      Removed value: -"Result"
    • removedOutput schema / title
      Removed value: -"delete_folderOutput"
    • addedOutput schema / x-fastmcp-wrap-result
      Added value: +true
  2. First observedv1.0.0

TDQS

A3.6/5.0
Behavior3/5

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

The description discloses that it returns the folder id on success or a ToolError on failure. However, with no annotations provided, it omits critical behavioral details like whether deletion is recursive, permission requirements, or irreversibility.

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 reasonably concise, using a docstring-like format with param and returns. It is front-loaded with the main action but could be more streamlined by removing redundant statements about error returns.

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

Completeness3/5

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

Given the tool's simplicity (single required parameter) and the presence of an output schema, the description covers the basics. However, it lacks important context about effects on children, permissions, and when to use this over other folder operations.

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?

The description adds a semantic description for the id_or_path parameter, clarifying it accepts either an ID or a path. Despite the schema having 0% description coverage, this is only a minimal addition beyond the parameter name itself.

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 tool name and description clearly state that it deletes a folder, using a specific verb and resource. It distinguishes itself from sibling tools like create_folder and update_folder by focusing on deletion.

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 when a folder deletion is needed, but provides no explicit guidance on when to use this tool versus alternatives (e.g., update_folder) or when not to use it.

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