Skip to main content
Glama
appwrite

Appwrite MCP Server

Official
by appwrite

tables_db_delete_index

Remove an index from a database table to optimize storage or modify data structure. Specify database, table, and index key to execute deletion.

Instructions

Delete an index.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
database_idYesDatabase ID.
table_idYesTable ID. You can create a new table using the TablesDB service [server integration](https://appwrite.io/docs/references/cloud/server-dart/tablesDB#createTable).
keyYesIndex Key.

Implementation Reference

  • Generic MCP tool execution handler. For 'tables_db_delete_index', retrieves the bound TablesDB.delete_index method from registry and invokes it with arguments.
    @server.call_tool()
    async def handle_call_tool(
        name: str, arguments: dict | None
    ) -> list[types.TextContent | types.ImageContent | types.EmbeddedResource]:
        
        try:
            tool_info = tools_manager.get_tool(name)
            if not tool_info:
                raise McpError(f"Tool {name} not found")
            
            bound_method = tool_info["function"]
            result = bound_method(**(arguments or {}))
            if hasattr(result, 'to_dict'):
                result_dict = result.to_dict()
                return [types.TextContent(type="text", text=str(result_dict))]
            return [types.TextContent(type="text", text=str(result))]
        except AppwriteException as e:
            return [types.TextContent(type="text", text=f"Appwrite Error: {str(e)}")]
        except Exception as e:
            return [types.TextContent(type="text", text=f"Error: {str(e)}")]
  • Dynamically generates tool metadata including input schema from method signatures, type hints, and docstrings of the underlying Appwrite service instance (TablesDB).
    def list_tools(self) -> Dict[str, Dict]:
        """Lists all available tools for this service"""
        tools = {}
    
        for name, func in inspect.getmembers(self.service, predicate=inspect.ismethod):
            if name.startswith('_'): # Skip private methods
                continue
    
            original_func = func.__func__
            
            # Skip if not from the service's module
            if original_func.__module__ != self.service.__class__.__module__:
                continue
    
            # Get the overridden name if it exists
            tool_name = self._method_name_overrides.get(name, f"{self.service_name}_{name}")
    
            docstring = parse(original_func.__doc__)
            signature = inspect.signature(original_func)
            type_hints = get_type_hints(original_func)
    
            properties = {}
            required = []
    
            for param_name, param in signature.parameters.items():
                if param_name == 'self':
                    continue
    
                param_type = type_hints.get(param_name, str)
                properties[param_name] = self.python_type_to_json_schema(param_type)
                properties[param_name]["description"] = f"Parameter '{param_name}'"
                
                for doc_param in docstring.params:
                    if doc_param.arg_name == param_name:
                        properties[param_name]["description"] = doc_param.description
    
                if param.default is param.empty:
                    required.append(param_name)
    
            tool_definition = Tool(
                name=tool_name,
                description=f"{docstring.short_description or "No description available"}",
                inputSchema={
                    "type": "object",
                    "properties": properties,
                    "required": required
                }
            )
            
            tools[tool_name] = {
                "definition": tool_definition,
                "function": func
            }
            
        return tools
  • Explicit registration of TablesDB service when --tables-db flag is provided, enabling tools prefixed with 'tables_db_' including 'tables_db_delete_index'.
    tools_manager.register_service(Service(TablesDB(client), "tables_db"))
  • Default registration of TablesDB service if no service flags specified, enabling 'tables_db_delete_index' tool.
    tools_manager.register_service(Service(TablesDB(client), "tables_db"))
  • Generates tool name 'tables_db_delete_index' by prefixing service_name 'tables_db' to method name 'delete_index' since no override.
    tool_name = self._method_name_overrides.get(name, f"{self.service_name}_{name}")
Behavior2/5

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

With no annotations provided, the description carries full burden but offers minimal behavioral insight. 'Delete' implies a destructive mutation, but it doesn't disclose permissions required, whether the deletion is reversible, potential side effects (e.g., impact on query performance), or error conditions. This is inadequate for a mutation tool with zero annotation coverage.

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 a single, efficient sentence with no wasted words, making it front-loaded and easy to parse. However, it's overly concise to the point of under-specification, lacking necessary details for a mutation tool. It earns a 4 for brevity but loses points for not being sufficiently informative.

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

Completeness2/5

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

Given this is a destructive mutation tool with no annotations and no output schema, the description is incomplete. It doesn't cover behavioral aspects like safety, permissions, or return values, and while parameters are covered by the schema, the overall context for safe and correct usage is lacking. This is insufficient for a tool that modifies data.

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 parameters are fully documented in the schema. The description adds no additional meaning beyond the schema, such as explaining relationships between parameters (e.g., that 'key' identifies the index within the table) or usage examples. Baseline 3 is appropriate when schema does the heavy lifting.

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

Purpose3/5

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

The description 'Delete an index' clearly states the action (delete) and resource (index), which is better than a tautology. However, it lacks specificity about what type of index (e.g., database index) and doesn't distinguish from sibling tools like 'tables_db_delete_column' or 'tables_db_delete_table', which also delete resources but different ones. It's vague about scope and context.

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool versus alternatives. The description doesn't mention prerequisites (e.g., needing an existing index), exclusions, or comparisons to siblings like 'tables_db_get_index' for reading or 'tables_db_create_index' for creating. This leaves the agent without context for tool selection.

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/appwrite/mcp-for-api'

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