Column Descriptions
Column descriptions are human-readable annotations attached to database columns that explain what each column contains and how its values should be interpreted.
In Depth
Column names compress meaning until it disappears: "amt_n" could be net amount, normalized amount, or amount in naira. Column descriptions restore the meaning—a sentence per column saying what it holds, its units, and its gotchas ("in cents, not dollars; null means pending"). Most databases support storing these as column comments, yet most teams never fill them in. The cost of that gap has gone up in the AI era: column descriptions are among the highest-value context you can give an AI query system, often turning ambiguous questions into correct SQL. Ten minutes documenting your twenty most-queried columns pays back immediately.
How AI for Database Helps
AI for Database uses your schema and column metadata to interpret questions correctly—well-described columns make plain-English answers sharper.
Related Terms
Data Dictionary
A data dictionary is a centralized reference that documents every table and column in a database—what it contains, what its values mean, and how it should be used.
Schema Linking
Schema linking is the step in text-to-SQL where words in a user's question are matched to the specific tables and columns in the database that they refer to.
Business Glossary for AI
A business glossary for AI is a curated set of definitions for company-specific terms—what counts as an "active user", how "revenue" is calculated—provided to an AI system so it interprets questions the way the business does.
Schema Introspection
Schema introspection is the automatic process of reading a database's own metadata to discover its tables, columns, data types, keys, and relationships.
Ready to try AI for Database?
Query your database in plain English. No SQL required. Start free today.
Free plan available · No credit card required