Columns (id, name, type, options) and saved views of a database, without rows. Check it before writing rows or changing views.
| Name | Required | Description | Default |
|---|---|---|---|
| databaseId | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| views | Yes | Saved views — always at least one | |
| schema | Yes | Column definitions (id, name, type, options) |
Changes observed during successful MCP inspections.
Input schema / properties / databaseId / descriptionRemoved value: -"Database ID (from list_workspace or search)"Output schema / properties / name / descriptionRemoved value: -"Database name"Output schema / properties / views / descriptionPrevious value: -"Saved views (id, name, config — table/kanban/calendar), always at least one"New value: +"Saved views — always at least one"Output schema / properties / viewsAdded value: +{
+ "description": "Saved views (id, name, config — table/kanban/calendar), always at least one",
+ "items": {},
+ "type": "array"
+}Output schema / requiredPrevious value: -[
- "name",
- "schema"
-]New value: +[
+ "name",
+ "schema",
+ "views"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds concrete return-content boundaries (no rows) and a recommended precondition that goes beyond the readOnlyHint. It is consistent with the readOnlyHint and openWorldHint false, and no contradictions.
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?
One sentence with dense, front-loaded content: return contents first, then the use trigger. No filler.
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 one-parameter read-only tool with an output schema and readOnlyHint, the description supplies the key boundary (schema vs rows) and the intended call timing. Nothing essential is missing.
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?
There is no parameter explanation in the description, and schema coverage is 0%, so the description was expected to compensate. The single databaseId is self-explanatory from its name, but the description adds no format, origin, or usage detail beyond the schema.
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?
The description names the resource ('a database') and a specific verb ('get'), enumerates the exact contents (columns id/name/type/options and saved views), and explicitly excludes rows. This lets an agent distinguish it from row-returning siblings like query_database.
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?
It states a clear trigger: 'Check it before writing rows or changing views.' It does not explicitly name sibling alternatives or state when not to use it, but the 'without rows' caveat implies row queries belong elsewhere.
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.