Skip to main content
Glama
Sign In
mssql-readonly-mcp

mssql-readonly-mcp

by riyama46
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

describe_table

Read-only

Retrieves column definitions for a specified table, including data types, nullability, primary and foreign keys, and referenced tables, so you can inspect its structure before writing queries.

Instructions

Columns of one table: type, nullability, primary/foreign keys and what each foreign key points to.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "table": "<table>"
    },
    "name": "describe_table"
  }
}

Input Schema

NameRequiredDescriptionDefault
tableYesTable name without schema, e.g. "employees"
schemaNoSchema name, e.g. "hr"dbo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.6/5.0
Behavior3/5

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

The annotations already declare a read-only, non-destructive, closed-world operation, so the safety profile carries little weight here. The description does add real value by disclosing the shape of the returned metadata (types, nullability, keys, FK targets), which matters because there is no output schema. It does not say what happens for a missing or ambiguous table, nor whether views are covered.

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?

A single compact sentence that leads with the resource and then lists the returned fields in priority order. No filler, no redundancy with the title or schema.

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

Completeness4/5

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

For a simple two-parameter read-only tool with a fully documented schema and no output schema, the description covers the essential return content in one line. The remaining gap is edge-case behavior (missing table, case sensitivity, view coverage), which is minor for this complexity level.

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%, and both parameters are documented with examples and a default for schema in the schema itself. The description adds only the implicit notion that the table parameter selects a single table; it provides no extra syntax or qualification detail beyond the structured fields.

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 names a specific resource (columns of one table) and enumerates exactly what metadata is returned: type, nullability, primary/foreign keys, and foreign key targets. It is a noun phrase rather than a verb, and it does not name or contrast with list_tables or run_query, so an agent must infer the boundary rather than read it.

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

Usage Guidelines3/5

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

There is no explicit when-to-use or when-not-to-use statement. The phrase 'Columns of one table' implies schema introspection scoped to a single table, which is enough to guess it is the alternative to run_query for inspecting structure, but the definition never states that or mentions prerequisites such as needing to know the table name first.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools