describe_column

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does disclose the primary behavior: numeric columns yield min, max, mean, median, null count; categorical columns yield unique count and top categories. This is helpful and beyond what a schema typically states. However, it does not mention edge cases (e.g., missing column, mixed types), error behavior, or limits on 'top frequent categories', leaving some uncertainty.

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 sentences, both front-loaded with the core purpose. The numeric vs categorical distinction is presented efficiently without filler. Every word adds value, and the structure is ideal for quick agent scanning.

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?

The tool has an output schema (not shown here), which reduces the need to describe return formats. The description covers the main cases and tells the agent what to expect. Minor gaps remain: no mention of read-only nature, error handling, or behavior on non-existent columns. For a simple one-parameter tool, this is nearly complete, hence a 4.

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 schema has 0% description coverage for the 'column' parameter (no description, no enum), so the description must compensate. It only states 'a specified column in the customers table', which adds minimal meaning beyond the parameter name itself. It does not explain that the column must exist, expected data types, or how invalid columns are handled. Given the low schema coverage, this is inadequate.

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 states that it 'Provides statistical summaries for a specified column in the customers table,' clearly identifying the resource (customers table column) and the deliverable (statistical summaries). It distinguishes itself from siblings like list_columns (which lists columns) and run_readonly_sql (which runs arbitrary queries) by its focus on computed summaries, and the numeric/categorical breakdown adds specificity. However, the verb 'provides' is generic; 'computes' or 'returns' would be stronger.

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 explicit guidance is given on when to use this tool versus alternatives. It implies usage by describing what it returns, but does not mention siblings like run_readonly_sql or get_dataset_info as alternatives, nor suggest trade-offs. An agent must infer that this is the right choice for column-level statistics, which is not guaranteed given the sibling list includes a generic SQL tool.

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