Skip to main content
Glama
wenb1n-dev

mysql_mcp_server

get_table_desc

Retrieve table structure details from a MySQL database by specifying table names. Supports multiple table queries and provides insights into database schema for efficient analysis.

Instructions

根据表名搜索数据库中对应的表结构,支持多表查询

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
textYes要搜索的表名

Implementation Reference

  • The GetTableDesc class is the main handler for the 'get_table_desc' tool. It defines the tool's name, description, input schema, and the run_tool method that constructs and executes a SQL query to retrieve table column information (name and comment) from information_schema.COLUMNS for the given table names.
    class GetTableDesc(BaseHandler):
        name = "get_table_desc"
        description = (
            "根据表名搜索数据库中对应的表字段,支持多表查询(Search for table structures in the database based on table names, supporting multi-table queries)"
        )
    
        def get_tool_description(self) -> Tool:
            return Tool(
                name=self.name,
                description=self.description,
                inputSchema={
                    "type": "object",
                    "properties": {
                        "text": {
                            "type": "string",
                            "description": "要搜索的表名"
                        }
                    },
                    "required": ["text"]
                }
            )
    
        async def run_tool(self, arguments: Dict[str, Any]) -> Sequence[TextContent]:
                """获取指定表的字段结构信息
    
                参数:
                    text (str): 要查询的表名,多个表名以逗号分隔
    
                返回:
                    list[TextContent]: 包含查询结果的TextContent列表
                    - 返回表的字段名、字段注释等信息
                    - 结果按表名和字段顺序排序
                    - 结果以CSV格式返回,包含列名和数据
                """
                try:
                    if "text" not in arguments:
                        raise ValueError("缺少查询语句")
    
                    text = arguments["text"]
    
                    config = get_db_config()
                    execute_sql = ExecuteSQL()
    
                    # 将输入的表名按逗号分割成列表
                    table_names = [name.strip() for name in text.split(',')]
                    # 构建IN条件
                    table_condition = "','".join(table_names)
                    sql = "SELECT TABLE_NAME, COLUMN_NAME, COLUMN_COMMENT "
                    sql += f"FROM information_schema.COLUMNS WHERE TABLE_SCHEMA = '{config['database']}' "
                    sql += f"AND TABLE_NAME IN ('{table_condition}') ORDER BY TABLE_NAME, ORDINAL_POSITION;"
                    return await execute_sql.run_tool({"query":sql})
    
                except Exception as e:
                    return [TextContent(type="text", text=f"执行查询时出错: {str(e)}")]
  • The BaseHandler's __init_subclass__ method automatically registers any subclass (like GetTableDesc) to the ToolRegistry upon class definition, using the tool's name as the key.
    def __init_subclass__(cls, **kwargs):
        """子类初始化时自动注册到工具注册表"""
        super().__init_subclass__(**kwargs)
        if cls.name:  # 只注册有名称的工具
            ToolRegistry.register(cls)
  • Import of GetTableDesc in handles/__init__.py triggers the loading of the module and class definition, which in turn automatically registers the tool via BaseHandler's __init_subclass__.
    from .get_table_desc import GetTableDesc
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool searches for table structures and supports multi-table queries, but lacks details on permissions, rate limits, error handling, or output format. For a database query tool with zero annotation coverage, this is a significant gap in transparency about how the tool behaves in practice.

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 in Chinese that conveys the core functionality without unnecessary words. It's front-loaded with the main purpose and includes an additional feature (multi-table query support). However, it could be slightly more structured by separating key points, but overall it's concise and to the point.

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 a database query tool with no annotations and no output schema, the description is incomplete. It doesn't explain what '表结构' (table structures) includes (e.g., columns, data types, constraints), how results are returned, or any limitations. For a tool that likely returns detailed metadata, more context is needed to guide effective use.

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 input schema has 100% description coverage, with the parameter 'text' documented as '要搜索的表名' (table name to search). The description adds minimal value beyond this, only implying that multiple table names might be supported via '多表查询' (multi-table queries), but doesn't specify syntax or format. With high schema coverage, the baseline score of 3 is appropriate as the schema does the heavy lifting.

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: searching for table structures in a database by table name, with support for multi-table queries. It specifies the verb ('搜索' - search) and resource ('表结构' - table structures), making the function understandable. However, it doesn't explicitly differentiate from sibling tools like get_table_name or get_table_index, which likely serve related but distinct purposes.

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. It mentions support for multi-table queries but doesn't clarify scenarios where this is preferable over other tools like get_table_name (which might retrieve table names without structures) or execute_sql (which could query data directly). There's no mention of prerequisites, limitations, or typical use cases.

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

Related 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/wenb1n-dev/mysql_mcp_server_pro'

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