Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral disclosure burden. It discloses meaningful behaviors beyond the schema: grouping commas and currency symbols are handled, non-numeric rows are excluded, and excluded rows are counted. This gives the agent realistic expectations about data cleaning.

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 sentence conveys the operation, the target resource, the computed metrics, and the edge-case handling with no filler. Every clause earns its place.

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 is sufficiently complete: it names the expected inputs, the statistics returned, and the preprocessing behavior. Minor omissions like the exact output shape or behavior when the column does not exist are not critical for a stats tool.

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% and the parameter is simply named 'column' with minLength 1. The description compensates by specifying that the column must be numeric, and that formatting and non-numeric values are handled in a particular way. It does not list valid column names, but that is reasonable for a single parameter.

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 a specific operation — computing summary statistics on a numeric column — and enumerates the exact outputs (count, min, max, mean, median, sum). This clearly distinguishes it from sibling tools like dataset_search, dataset_row, and dataset_compare.

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 implies when to use the tool: when summary statistics of a numeric column are needed, and it clarifies that only numeric columns are supported. However, it does not explicitly state when-not-to-use or mention alternatives such as dataset_columns for listing valid columns or dataset_top for sample rows.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.