Run SQL (CREATE TABLE / INSERT / UPDATE / DELETE / ALTER) against this workspace's own database. Use db.schema first to see what exists, and db.query to read.
| Name | Required | Description | Default |
|---|---|---|---|
| sql | Yes | SQL DDL/DML, e.g. CREATE TABLE records (id serial primary key, name text) | |
| in_workspace | No | Run this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected. |
Changes observed during successful MCP inspections.
Input schema / properties / in_workspaceAdded value: +{
+ "description": "Run this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.",
+ "type": "integer"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations declare destructiveHint=false, yet the description explicitly advertises DELETE and ALTER — irreversible data loss and schema mutation against a live database. An agent reading both gets directly conflicting safety signals about whether this call can destroy data, which is the highest-stakes fact for this tool. The dot-notation references ("db.schema", "db.query") also do not match the real sibling names db_schema/db_query.
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?
Two sentences, zero filler, with the operation scope front-loaded ahead of the routing advice. Every clause earns its place.
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?
For a 2-parameter write tool with no output schema and full schema coverage, the description covers purpose, scope and sequencing adequately; return behavior need not be explained. It stops short of the completeness bar because it leaves the destructive/irreversible consequences of DELETE/ALTER unstated and conflicts with the safety annotations.
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?
Schema description coverage is 100% and both parameters are documented in the input schema, including the in_workspace isolation semantics ("Nothing is stored; other sessions are not affected"). The description adds no parameter-level detail of its own, so the baseline 3 applies.
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?
States a specific verb (Run SQL) plus the exact resource and scope: DDL/DML against "this workspace's own database," and enumerates the operations (CREATE TABLE / INSERT / UPDATE / DELETE / ALTER). It also positions itself against db_query (read) and db_schema (inspect), so an agent can distinguish it from its closest siblings without opening a schema.
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?
Gives explicit sequencing and routing: "Use db.schema first to see what exists, and db.query to read." This is a when-to-use and when-to-use-something-else statement in one sentence, which is exactly what an agent needs to pick between db_execute, db_schema and db_query.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.