dataset_statscount, min, max, mean, median and sum of a numeric column of the Abutly dataset (grouping commas and currency are handled; non-numeric rows are excluded and counted).
| Name | Required | Description | Default |
|---|---|---|---|
| column | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the disclosure burden, and it does more than repeat the title: it discloses that grouping commas and currency symbols are parsed, and that non-numeric rows are excluded and counted. This is meaningful behavioral context. The phrase 'excluded and counted' is slightly ambiguous about whether the returned count excludes those rows, so it is not a perfect 5.
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 compact sentence lists the exact statistics, then adds two important caveats in a parenthetical. There is no filler; the most identifying information (statistics and dataset) comes first, and the edge-case behavior is placed where it cannot distract.
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 one-parameter tool with no output schema, the description supplies the return statistics, the target dataset, and data-cleaning semantics. It does not specify the exact response shape or define the behavior when the column contains no numeric rows, but those are minor omissions for this simple operation.
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 coverage is 0%, so the description must add semantics. It does: 'column' is specified as a numeric column of the Abutly dataset rather than just any string. The mention of grouping commas, currency, and non-numeric handling also informs what kind of values the column may contain, which goes beyond the bare 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 clearly identifies the operation: it computes count, min, max, mean, median, and sum for a numeric column. The title reinforces this, and the scope is narrowed to 'the Abutly dataset,' distinguishing it from sibling tools like dataset_search or dataset_top, which serve different lookup/ranking purposes.
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?
The description makes the usage context clear: use this when summary statistics for a numeric column are needed. It does not explicitly name alternatives or exclusion conditions, so it falls short of a 5, but the numeric-column and dataset qualifiers are enough for an agent to select it over the listed siblings.
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.
Each tool has a clearly distinct role: schema inspection, provenance, exact lookup, substring search, multi-value comparison, numeric stats, and top/bottom ranking. Even though dataset_row and dataset_compare both retrieve rows by column value, their descriptions make the single-value vs multi-value distinction clear.
All tools share a consistent dataset_ prefix and use clear snake_case names. The suffixes are either nouns or verbs that accurately reflect the operation, making the naming predictable and easy to navigate.
Seven tools is well-scoped for a single-dataset query server. Each tool covers a distinct query need without redundancy or bloat.
The toolset covers the full range of dataset querying: schema inspection, provenance, exact match, substring search, multi-value comparison, numeric aggregation, and ranking. Since this is a read-only dataset server, no update/create/delete tools are needed.