introspect_schemaRetrieve database tables and columns in an LLM-friendly format before writing SQL queries against an existing database.
Get the database schema — tables and columns — in a format optimized for LLM context. Use this before writing queries against an existing database.
| Name | Required | Description | Default |
|---|---|---|---|
| databaseId | Yes | The database ID to introspect |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the output format (LLM-optimized) and use case, but omits important behavioral details: whether it requires specific permissions, whether it caches results, how large schemas are handled, or the exact response structure beyond 'tables and columns'. This is a gap for a read-only tool with no annotation coverage.
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 concise sentences: the first defines output, the second gives usage timing. No waste, front-loaded with core purpose.
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 description covers purpose, output format orientation, and a basic usage hint. However, for a tool with no annotations, no output schema, and only one parameter, it lacks adequate behavioral disclosure (permissions, performance, error handling) and alternative comparisons. It is minimally adequate but not complete.
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%, so the single parameter (databaseId) is fully documented in the schema. The description adds no parameter-specific information. Baseline 3 is appropriate when the schema handles parameter semantics completely.
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 (introspect) and resource (database schema: tables and columns), and specifies the output format orientation (optimized for LLM context). This clearly distinguishes it from sibling tools like get_database or list_databases, which imply metadata about the database itself rather than its internal 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?
Provides timing guidance ('Use this before writing queries against an existing database'), which is useful context. However, it does not compare against alternatives (e.g., why not use get_database or query with DESCRIBE?), nor does it mention exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.