get_data_profile

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

No annotations are provided, so the description carries the burden; it compensates by disclosing output fields, the approximate nature of distinct counts, and the DuckDB SUMMARIZE implementation with large-table efficiency. It does not explicitly state that the operation is read-only, but the 'get' verb and summary-statistics framing strongly imply no mutation.

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?

The description is compact: one purpose sentence, one implementation/performance sentence, and a one-item Args entry. Every sentence earns its place, and the most important information is front-loaded.

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?

With only one parameter and no output schema, the description gives essential output details and input provenance, making selection and invocation feasible. It lacks a precise return-shape description and explicit alternative guidance, but the listed statistics and sibling tool names provide sufficient context.

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 only 'dataset' with a title and no description (0% coverage), while the description's Args section adds actionable semantics: 'Exact table or view name, as returned by list_datasets.' This fully clarifies the value format and provides the source for valid inputs.

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 opens with a specific action ('Generate summary statistics') and explicitly enumerates the output fields (type, null percentage, approximate distinct count, min/max, mean/stddev/quartiles). This clearly distinguishes it from siblings like get_schema and get_row_count by covering full-column profiling rather than just schema or row count.

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 supplies a concrete prerequisite ('dataset: Exact table or view name, as returned by list_datasets') and notes performance suitability for large tables via DuckDB's SUMMARIZE. It stops short of explicitly naming sibling alternatives or stating when not to use this tool, but the intended context is clear.

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