Skip to main content
Glama

get_object_details

Retrieve detailed information about PostgreSQL database objects like tables, views, sequences, or extensions to understand their structure and properties.

Instructions

Show detailed information about a database object

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
schema_nameYesSchema name
object_nameYesObject name
object_typeNoObject type: 'table', 'view', 'sequence', or 'extension'table

Implementation Reference

  • The `get_object_details` tool implementation which retrieves details for tables, views, sequences, and extensions from the database and returns them formatted as text.
    @mcp.tool(description="Show detailed information about a database object")
    async def get_object_details(
        schema_name: str = Field(description="Schema name"),
        object_name: str = Field(description="Object name"),
        object_type: str = Field(description="Object type: 'table', 'view', 'sequence', or 'extension'", default="table"),
    ) -> ResponseType:
        """Get detailed information about a database object."""
        try:
            sql_driver = await get_sql_driver()
    
            if object_type in ("table", "view"):
                # Get columns
                col_rows = await SafeSqlDriver.execute_param_query(
                    sql_driver,
                    """
                    SELECT column_name, data_type, is_nullable, column_default
                    FROM information_schema.columns
                    WHERE table_schema = {} AND table_name = {}
                    ORDER BY ordinal_position
                    """,
                    [schema_name, object_name],
                )
                columns = (
                    [
                        {
                            "column": r.cells["column_name"],
                            "data_type": r.cells["data_type"],
                            "is_nullable": r.cells["is_nullable"],
                            "default": r.cells["column_default"],
                        }
                        for r in col_rows
                    ]
                    if col_rows
                    else []
                )
    
                # Get constraints
                con_rows = await SafeSqlDriver.execute_param_query(
                    sql_driver,
                    """
                    SELECT tc.constraint_name, tc.constraint_type, kcu.column_name
                    FROM information_schema.table_constraints AS tc
                    LEFT JOIN information_schema.key_column_usage AS kcu
                      ON tc.constraint_name = kcu.constraint_name
                     AND tc.table_schema = kcu.table_schema
                    WHERE tc.table_schema = {} AND tc.table_name = {}
                    """,
                    [schema_name, object_name],
                )
    
                constraints = {}
                if con_rows:
                    for row in con_rows:
                        cname = row.cells["constraint_name"]
                        ctype = row.cells["constraint_type"]
                        col = row.cells["column_name"]
    
                        if cname not in constraints:
                            constraints[cname] = {"type": ctype, "columns": []}
                        if col:
                            constraints[cname]["columns"].append(col)
    
                constraints_list = [{"name": name, **data} for name, data in constraints.items()]
    
                # Get indexes
                idx_rows = await SafeSqlDriver.execute_param_query(
                    sql_driver,
                    """
                    SELECT indexname, indexdef
                    FROM pg_indexes
                    WHERE schemaname = {} AND tablename = {}
                    """,
                    [schema_name, object_name],
                )
    
                indexes = [{"name": r.cells["indexname"], "definition": r.cells["indexdef"]} for r in idx_rows] if idx_rows else []
    
                result = {
                    "basic": {"schema": schema_name, "name": object_name, "type": object_type},
                    "columns": columns,
                    "constraints": constraints_list,
                    "indexes": indexes,
                }
    
            elif object_type == "sequence":
                rows = await SafeSqlDriver.execute_param_query(
                    sql_driver,
                    """
                    SELECT sequence_schema, sequence_name, data_type, start_value, increment
                    FROM information_schema.sequences
                    WHERE sequence_schema = {} AND sequence_name = {}
                    """,
                    [schema_name, object_name],
                )
    
                if rows and rows[0]:
                    row = rows[0]
                    result = {
                        "schema": row.cells["sequence_schema"],
                        "name": row.cells["sequence_name"],
                        "data_type": row.cells["data_type"],
                        "start_value": row.cells["start_value"],
                        "increment": row.cells["increment"],
                    }
                else:
                    result = {}
    
            elif object_type == "extension":
                rows = await SafeSqlDriver.execute_param_query(
                    sql_driver,
                    """
                    SELECT extname, extversion, extrelocatable
                    FROM pg_extension
                    WHERE extname = {}
                    """,
                    [object_name],
                )
    
                if rows and rows[0]:
                    row = rows[0]
                    result = {"name": row.cells["extname"], "version": row.cells["extversion"], "relocatable": row.cells["extrelocatable"]}
                else:
                    result = {}
    
            else:
                return format_error_response(f"Unsupported object type: {object_type}")
    
            return format_text_response(result)
        except Exception as e:
            logger.error(f"Error getting object details: {e}")
            return format_error_response(str(e))
Behavior2/5

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

No annotations provided, yet the description discloses no behavioral traits beyond the obvious read-only implication of 'Show.' Fails to specify what 'detailed information' includes (structure, metadata, statistics), whether the operation is safe, idempotent, or any error conditions.

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?

Single sentence with zero redundancy or filler. However, given the lack of annotations and output schema, the description is arguably underweight rather than efficiently concise.

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?

Inadequate for a tool with no annotations and no output schema. The description fails to hint at return value structure, complexity level (e.g., 'includes column definitions and constraints'), or how it complements other database introspection tools.

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 coverage is 100%, so the schema adequately documents all three parameters including the default value and valid options for object_type. The description adds no parameter-specific context, qualifying for the baseline score of 3.

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?

States the basic action (Show) and resource (database object) but is generic. 'Detailed information' is vague, and the description fails to differentiate from sibling tool list_objects (which returns multiple items vs. this single-object focus).

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?

Provides no guidance on when to use this tool versus alternatives like list_objects or list_schemas. No mention of prerequisites (e.g., knowing schema_name from list_schemas first) or intended workflow.

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/moecodeshere/mcptrial'

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