Generate initial SQL DDL for a schema in the model's SQL dialect without executing it. For existing databases, use a separately reviewed migration instead.
Generate initial DDL for the model's SQL dialect. No SQL execution. Existing databases require a separately reviewed change migration.
| Name | Required | Description | Default |
|---|---|---|---|
| schema | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish read-only, idempotent, non-destructive behavior, so the bar is lowered, yet the description still adds real context: it emits DDL text only and never executes SQL, and it will not produce a migration for an existing database. It does not say how the output is returned or whether dialect selection is inferred, but the behavioral picture is solid.
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?
Three short sentences, front-loaded with the core action and each carrying a distinct piece of information: what is produced, what is not executed, and the migration caveat. No filler or redundancy.
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?
Safety and scoping are fully covered and there is no output schema to explain, but a tool whose sole required input is an undescribed nested object is incomplete on the input side. The dialect-selection behavior is also left implicit.
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 single required 'schema' parameter is a nested object with additionalProperties allowed and 0% schema description coverage, so the schema itself explains nothing. The description never says what shape that object must take or what fields it expects, leaving the only required input effectively 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 and output artifact: generate initial DDL for the model's SQL dialect. That is enough to distinguish it in spirit from a sibling like export_java, but no sibling is named or contrasted explicitly, so the differentiation is inferred rather than stated.
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 a genuine when-not: existing databases should go through a 'separately reviewed change migration' path rather than this tool. That exclusion is clear and actionable, but there is no explicit when-to-use trigger and no named alternative tool, so it stops short of a full 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.