Run any SQL query to interact with your PostgreSQL database.
Execute any SQL query
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "execute_sql"
}
}| Name | Required | Description | Default |
|---|---|---|---|
| sql | No | SQL to run | all |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations include destructiveHint=true, which already alerts the agent to potential destructive side effects. The description's 'any' reinforces that the tool can execute non-read queries, but it adds no additional behavioral context such as permission requirements, transaction handling, or result format. This is a minimal contribution beyond the structured hint.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description consists of one concise sentence, 'Execute any SQL query', which is immediately front-loaded and free of unnecessary elaboration. It optimizes brevity while conveying the essential action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is a simple SQL executor with a single parameter and an output schema, and the annotation provides a destructive warning. However, the description gives no context about when to use it (e.g., for arbitrary reads/writes) versus the specialized sibling tools, and it omits any caveats about side effects beyond the bare annotation. Given the tool's low complexity, this is adequate but not enriched, so it falls short of being fully contextual.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema provides a single `sql` parameter with a description ('SQL to run') and a default, achieving 100% coverage. The tool description 'Execute any SQL query' adds no further meaning about the parameter's syntax, allowed statements, or formatting. Since the schema already documents the parameter, no compensating explanation is needed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Execute any SQL query' clearly states the tool's verb (execute) and resource (SQL query), making its core function unambiguous. However, it does not explicitly differentiate from sibling tools like explain_query or analyze_query_indexes, leaving the reader to infer its role as a general-purpose executor. This is clear but lacks explicit sibling differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 doesn't mention that this is for arbitrary SQL execution while siblings handle query analysis, schema listing, or index insights, nor does it state any restrictions or prerequisites. This leaves the agent without direction for tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.