Skip to main content
Glama
appwrite

Appwrite MCP Server

Official
by appwrite

tables_db_create_float_column

Add a float column to an Appwrite database table with optional min/max value constraints and default settings.

Instructions

Create a float column. Optionally, minimum and maximum values can be provided.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
database_idYesDatabase ID.
table_idYesTable ID.
keyYesColumn Key.
requiredYesIs column required?
minNoMinimum value
maxNoMaximum value
defaultNoDefault value. Cannot be set when required.
arrayNoIs column an array?

Implementation Reference

  • Explicit registration of the TablesDB service (via CLI --tables-db flag). Enables tools like 'tables_db_create_float_column' by wrapping TablesDB methods.
    if args.tables_db:
        tools_manager.register_service(Service(TablesDB(client), "tables_db"))
    if args.users:
  • Default registration of TablesDB service if no flags specified. Enables the tool.
    if not any([args.databases, args.tables_db, args.users, args.teams, args.storage,
                args.functions, args.messaging, args.locale, args.avatars, args.sites]):
        tools_manager.register_service(Service(TablesDB(client), "tables_db"))
  • Dynamically generates tool definitions (including schema) by introspecting service methods. For TablesDB.create_float_column, creates 'tables_db_create_float_column' tool with schema from signature.
    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
  • Generic MCP tool handler that retrieves the bound method from the registry (TablesDB.create_float_column) and executes it with provided arguments, returning the result.
    @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)}")]
  • Registers services and their tools into the central registry, enabling lookup by name for execution.
    def register_service(self, service: Service):
        """Register a new service and its tools"""
        self.services.append(service)
        self.tools_registry.update(service.list_tools())
Behavior2/5

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 states the tool creates a column (implying a mutation) and mentions optional min/max values, but lacks critical details like permission requirements, whether the operation is reversible, error conditions, or what happens to existing data. 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.

Conciseness5/5

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

The description is extremely concise with two sentences that directly state the purpose and a key optional feature. It is front-loaded and wastes no words, making it easy to parse quickly.

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 the complexity of creating a database column (a mutation operation), lack of annotations, and no output schema, the description is insufficient. It doesn't explain the return value, error handling, or side effects, leaving significant gaps for an AI agent to understand tool behavior.

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 fully documents all 8 parameters. The description adds minimal value by mentioning min and max as optional, which is already clear from the schema. No additional semantic context is provided beyond what the schema offers, meeting the baseline for high coverage.

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 action ('Create a float column') and resource, which is specific and distinguishes it from siblings like create_integer_column or create_string_column. However, it doesn't explicitly differentiate from other column creation tools beyond the data type, which is implied but not stated.

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?

The description provides no guidance on when to use this tool versus alternatives like create_integer_column or create_enum_column, nor does it mention prerequisites such as needing an existing database and table. It only mentions optional parameters (min/max) without contextual usage advice.

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