Find columns by name

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and a closed-world scope, so safety is covered. The description still adds behavioral value by disclosing the default inclusion of views and the content of each result (type_declaration and nullability).

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 tight clauses: the capability first, then the routing guidance. No filler, and the scope constraint (tables plus default views) 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 no output schema present, the description compensates by naming the returned fields (type_declaration, nullability) and the default view behavior. Combined with the fully documented input schema and safety annotations, an agent has everything needed to call it correctly.

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 description coverage is 100%, so the schema already documents all four parameters in detail, including the unanchored pattern semantics and the schema default. The description only echoes the view default and adds no parameter detail beyond the schema — the expected baseline of 3.

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?

States a specific verb and resource: finds every table and (by default) every view holding a column matching a name pattern. It also names the sibling tools (list_tables, list_views) that find objects by their own name, so an agent can discriminate without opening a schema.

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?

Gives explicit scenarios — before a rename, a widening, or an impact review — and explicitly routes the alternative case ('to find objects by their own name') to list_tables or list_views. When and when-not are both covered.

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