Skip to main content
Glama
Teradata

Teradata MCP Server

Official
by Teradata

qlty_standardDeviation

Calculate standard deviation for a specified column in Teradata to measure data dispersion and assess variability in your dataset.

Instructions

Get the standard deviation from column in a table.

Arguments: database_name - name of the database table_name - table name to analyze column_name - column name to analyze

Returns: ResponseType: formatted response with query results + metadata

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
database_nameYes
table_nameYes
column_nameYes

Implementation Reference

  • The handler function that executes the tool. It connects to Teradata, runs TD_UnivariateStatistics on the specified table and column to compute MEAN and STD, formats the results into JSON, adds metadata, and returns a formatted response.
    def handle_qlty_standardDeviation(
        conn: TeradataConnection,
        database_name: str | None,
        table_name: str,
        column_name: str,
        *args,
        **kwargs
    ):
        """
        Get the standard deviation from column in a table.
    
        Arguments:
          database_name - name of the database
          table_name - table name to analyze
          column_name - column name to analyze
    
        Returns:
          ResponseType: formatted response with query results + metadata
        """
        logger.debug(f"Tool: handle_qlty_standardDeviation: Args: table_name: {database_name}.{table_name}, column_name: {column_name}")
    
        if database_name is not None:
                table_name = f"{database_name}.{table_name}"
    
        with conn.cursor() as cur:
            rows = cur.execute(f"select * from TD_UnivariateStatistics ( on {table_name} as InputTable using TargetColumns ('{column_name}') Stats('MEAN','STD')) as dt ORDER BY 1,2")
            data = rows_to_json(cur.description, rows.fetchall())
            metadata = {
                "tool_name": "qlty_standardDeviation",
                "database_name": database_name,
                "table_name": table_name,
                "column_name": column_name,
                "stats_calculated": ["MEAN", "STD"],
                "rows": len(data)
            }
            logger.debug(f"Tool: handle_qlty_standardDeviation: Metadata: {metadata}")
            return create_response(data, metadata)
  • The code that dynamically loads tool modules based on profile, discovers all handle_* functions, derives the tool name by stripping 'handle_', and registers them as MCP tools using FastMCP's mcp.tool() decorator. This registers 'qlty_standardDeviation'.
    # Register code tools via module loader
    module_loader = td.initialize_module_loader(config)
    if module_loader:
        all_functions = module_loader.get_all_functions()
        for name, func in all_functions.items():
            if not (inspect.isfunction(func) and name.startswith("handle_")):
                continue
            tool_name = name[len("handle_"):]
            if not any(re.match(p, tool_name) for p in config.get('tool', [])):
                continue
            # Skip template tools (used for developer reference only)
            if tool_name.startswith("tmpl_"):
                logger.debug(f"Skipping template tool: {tool_name}")
                continue
            # Skip BAR tools if BAR functionality is disabled
            if tool_name.startswith("bar_") and not enableBAR:
                logger.info(f"Skipping BAR tool: {tool_name} (BAR functionality disabled)")
                continue
            # Skip chat completion tools if chat completion functionality is disabled
            if tool_name.startswith("chat_") and not enableChat:
                logger.info(f"Skipping chat completion tool: {tool_name} (chat completion functionality disabled)")
                continue
            wrapped = make_tool_wrapper(func)
            mcp.tool(name=tool_name, description=wrapped.__doc__)(wrapped)
            logger.info(f"Created tool: {tool_name}")
            logger.debug(f"Tool Docstring: {wrapped.__doc__}")
    else:
  • ModuleLoader configuration mapping 'qlty' prefix to the qlty tools module, enabling lazy loading of the qlty_standardDeviation handler when the qlty module is required by the profile.
    MODULE_MAP = {
        'bar': 'teradata_mcp_server.tools.bar',
        'base': 'teradata_mcp_server.tools.base',
        'chat': 'teradata_mcp_server.tools.chat',
        'dba': 'teradata_mcp_server.tools.dba',
        'fs': 'teradata_mcp_server.tools.fs',
        'qlty': 'teradata_mcp_server.tools.qlty',
        'rag': 'teradata_mcp_server.tools.rag',
        'sql_opt': 'teradata_mcp_server.tools.sql_opt',
        'sec': 'teradata_mcp_server.tools.sec',
        'tmpl': 'teradata_mcp_server.tools.tmpl',
        'plot': 'teradata_mcp_server.tools.plot',
        'tdvs': 'teradata_mcp_server.tools.tdvs'
    }
Behavior2/5

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

No annotations are provided, so the description carries full burden. It states it 'Returns: ResponseType: formatted response with query results + metadata,' which gives some behavioral insight into output format. However, it lacks critical details: whether this is a read-only operation, if it requires specific permissions, potential performance impact on large tables, or error handling for non-numeric columns.

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 concise with three clear sections: purpose statement, arguments list, and returns information. Every sentence earns its place, though the purpose statement could be slightly more precise (e.g., 'Calculate' instead of 'Get'). The structure is front-loaded with the main functionality.

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 3 parameters with 0% schema coverage and no output schema, the description provides basic parameter semantics and return format. However, for a statistical calculation tool with no annotations, it should include more behavioral context (e.g., computational characteristics, error conditions) and clearer differentiation from sibling tools to be complete.

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 0%, so the description must compensate. It lists all three parameters with brief explanations in the 'Arguments' section, adding meaning beyond the schema's property titles. However, it doesn't provide examples, constraints (e.g., valid database/table names), or clarify that 'database_name' can be null (per the schema's anyOf).

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: 'Get the standard deviation from column in a table.' It specifies the verb ('Get'), resource ('standard deviation'), and target ('column in a table'). However, it doesn't explicitly differentiate from sibling tools like 'qlty_univariateStatistics' or 'qlty_columnSummary' that might provide similar statistical analyses.

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. With many sibling tools (e.g., 'qlty_univariateStatistics', 'qlty_columnSummary', 'base_columnDescription'), there's no indication of when this specific standard deviation calculation is preferred or what distinguishes it from other quality analysis tools.

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/Teradata/teradata-mcp-server'

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