Safely introspect database tables, column types, nullable flags, primary keys, and foreign key relationships to inform queries and schema-aware code changes.
Safely introspect database tables, column types, nullable flags, primary keys, and foreign key relationships.
| Name | Required | Description | Default |
|---|---|---|---|
| tableName | No | Optional specific table name to inspect. If omitted, returns all tables. |
Changes observed during successful MCP inspections.
v0.2.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, so the description carries the full burden. 'Safely' signals a non-destructive read, and the enumeration of returned fields (types, nullability, PKs, FKs) gives a partial return-shape picture. It does not state permission requirements, whether views/system tables are included, or the response structure, and there is no output schema to cover that gap.
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 front-loaded sentence with no filler. The verb and the return contents appear immediately, and no wording is redundant.
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 simple read-only introspection tool with one optional parameter and no output schema, the description covers the core question of what information comes back. The remaining gap, the exact response shape and permission requirements, is modest given the tool's low complexity.
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 parameter has 100% schema description coverage, so the agent already knows that omitting tableName returns all tables. The description adds nothing beyond that schema text, which is the correct baseline for a one-parameter tool with full coverage.
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 tables') and enumerates exactly what is returned: column types, nullable flags, primary keys, foreign keys. An agent can distinguish it from db_query or db_commit on intent. It does not explicitly differentiate itself from the close sibling db_check_schema_drift, which keeps it at 4 rather than 5.
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?
No when-to-use guidance and no alternatives named. Given siblings like db_check_schema_drift and db_query, the agent is left to infer that this is the schema-discovery step, and that inference is only weakly supported by the word 'introspect'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.