Skip to main content
Glama
mcp-sql-gateway

mcp-sql-gateway

run_query

Executes a single read-only SELECT (SQLite dialect) against the governed SQL database, applying an enforced row limit to every result.

Instructions

Run a single read-only SELECT (SQLite dialect). A row limit is always applied.

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": {
      "sql": "<sql>"
    },
    "name": "run_query"
  }
}

Input Schema

NameRequiredDescriptionDefault
sqlYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations, the description carries the full burden and does disclose the key traits: read-only safety profile, SQLite dialect, one statement per call, and that a row limit is always enforced. It omits the limit's value, error/failure behavior, and whether the call is logged (relevant given the my_recent_queries sibling).

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?

Two short sentences, front-loaded with the core action and constraint, with no restatement of the title or padding.

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?

An output schema exists, so return-shape explanation is not required, and for a one-parameter query tool the safety profile and truncation notice cover most needs. Failure modes and the concrete row cap are the remaining gaps.

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 schema only labels the single parameter 'sql' with 0% description coverage; the description adds real meaning by fixing the dialect to SQLite and constraining the statement to a read-only SELECT. It still says nothing about accepted syntax edge cases such as trailing semicolons or quoting.

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?

States a specific verb and resource: run a single read-only SELECT against SQLite. That is clearly distinguishable from list_tables/describe_table, which inspect schema rather than execute queries, though no sibling is named explicitly.

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?

The 'single read-only SELECT' phrasing implies the boundary (no writes, no multi-statement scripts), but there is no explicit when-to-use guidance, such as preferring describe_table for schema introspection or list_tables instead of querying sqlite_master.

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