Run any single statement the user confirmed in the SQL Editor app (writes and DDL included).
Run any single statement the user confirmed in the SQL Editor app (writes and DDL included).
| Name | Required | Description | Default |
|---|---|---|---|
| sql | Yes | ||
| tab | No | ||
| file | No | ||
| tab_id | No | ||
| database | No | ||
| max_rows | No |
Changes observed during successful MCP inspections.
v0.9.0Input schema / properties / fileAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "File"
+}Input schema / properties / tabAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Tab"
+}Input schema / properties / tab_idAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Tab Id"
+}v0.8.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false and destructiveHint=true, so the safety profile is covered; 'writes and DDL included' partly restates that. The genuinely new context is the single-statement limit and the user-confirmation precondition, but nothing is said about transaction/commit behavior, permissions, or error handling for a destructive mutation tool.
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?
A single tight sentence, front-loaded with the verb and free of padding. It is appropriately sized for its scope, though briefly stating the max_rows/database defaults would have been low-cost.
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 six-parameter destructive tool with no output schema and zero schema coverage, one sentence is insufficient. An agent gets no guidance on tab/file/database targeting or the max_rows default, even though annotations at least carry the safety signal.
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 0% and none of the six parameters (tab, file, tab_id, database, max_rows) are explained in the description. Only 'single statement' loosely touches the sql parameter; the other five are left entirely undocumented.
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') and resource ('any single statement'), plus scope ('writes and DDL included') and context ('the SQL Editor app'). However, it does not distinguish itself from near-name siblings like sql_editor_query or the top-level run_sql, so an agent must infer which execution path applies.
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?
'Single statement' and 'the user confirmed' imply when to use it, giving an implicit constraint (one statement at a time, already approved). But no alternative is named and no when-not guidance is given, leaving the many sibling execute/query tools un-disambiguated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.