Get per-column row counts, NULLs, distinct values, min, and max in a single query to understand a column's grain and range before filtering or joining.
Per-column row count, NULLs, distinct values, min and max, in one aggregate query. Use it to learn a column's grain and range before filtering or joining on it. Up to 15 columns per call.
| Name | Required | Description | Default |
|---|---|---|---|
| table | Yes | ||
| columns | No | ||
| connection | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation already signals safety. The description adds useful behavioral constraints: it runs 'one aggregate query' and is limited to 'Up to 15 columns per call.' It does not cover error or edge-case behavior, but the annotation lowers the bar.
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 economical sentences: the first states outputs and mechanism, the second states the use case and the column limit. Every clause earns its place with no 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?
Covers the essential contract: what is computed, when to use it, and the column limit. Since there is no output schema, the listed metrics serve as the output contract. Minor ambiguity about omitted columns and the connection parameter prevents a perfect score.
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%, so the description must compensate. It does clarify the columns parameter via the 15-column limit and per-column metrics, and 'table' is obvious from context. However, it provides no semantics for the connection parameter or for what a null columns value means.
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 the exact aggregate metrics returned (row count, NULLs, distinct values, min/max) and ties them to a specific resource: columns of a table. This differentiates it from siblings like describe_table (schema metadata) and sample_table (row sampling) even though no sibling is named.
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?
Explicitly frames the use case: 'learn a column's grain and range before filtering or joining on it.' This gives clear context for when to call the tool, though it does not mention alternatives or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.