List the tables and views available through the configured SQLite database.

Use this read-only tool to discover relation names before profiling or testing. It accepts no arguments and never returns the database path or connection credentials. It does not extract data, so row-limit and null-handling behavior do not apply. It cannot list columns or execute SQL.

Profile one table using deterministic, rule-based heuristics.

Provide a conservative table identifier and an optional positive maximum row count. The server selects only that table's columns, orders rows deterministically, and clamps extraction to the configured hard limit. It reports whether first-N limiting truncated the table. SQL and sampling cannot be provided. Nulls remain excluded from summaries and are counted for every column. Suggested roles are advisory and use database/pandas type, primary-key metadata, cardinality, uniqueness, and null counts; no LLM is called. Examples are capped and suppressed for identifier or secret-like columns, but this tool is not a comprehensive PII detector.

Run one approved statistical test on a deterministic bounded table extract.

Use Welch welch_t_test for a two-sided independent-samples comparison of numeric means without an equal-variance assumption. Use the two-proportion two_proportion_z_test for a comparison of binary success proportions, and always provide the explicit success value; the server never guesses it. Both tests require a conservative table identifier, outcome and grouping columns, exactly two group values, alpha between 0 and 1, and an optional row cap. The configured hard row limit always applies; truncation and first-N bias are reported. Rows with null outcomes or groups are excluded and counted. Welch rejects non-numeric or non-finite outcomes and needs two observations per group. The proportion test requires an exactly binary selected outcome and at least five successes and five failures per group. Do not use either test for paired/repeated observations or causal conclusions. Results contain maintained-library statistics and p-values, effect sizes, assumptions, warnings, and audit metadata. Significance does not establish causality or business importance.