security_columns

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

Annotations already declare readOnlyHint=true, and the trailing "Read-only." merely restates that without adding anything. Beyond the annotation the description says nothing about whether results are permission-filtered, whether both database and table must exist beforehand, or what shape the returned column list takes — meaningful gaps for a tool with no output schema.

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 definition is a single compact sentence with the resource front-loaded, plus a short safety tag. The embedded quoted UI label is slightly awkward but not wasteful, and no padding sentences dilute the statement.

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?

For a simple two-parameter read tool with no output schema, the description should at minimum convey what a returned column entry contains and whether the caller must pass a fully qualified table. Neither is present, and the database parameter is entirely unaddressed, leaving the definition under-specified relative to its scope.

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 0%, so the description carries the full burden for the two required parameters, yet it only loosely implies a table and never mentions the required `database` parameter or the identifier format expected for either. An agent learns nothing about how to supply `database`/`table` beyond the bare property names.

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 phrase "Columns of one table" identifies the resource, but the verb is implicit (list) and the qualifier "for the column picker of 'Grant columns (through a view)'" frames the tool around a UI widget rather than a capability. It does not distinguish itself from the many column-listing siblings such as sas_columns, cas_columns, or security_tables, so an agent cannot tell which to pick on purpose alone.

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 mention of the "Grant columns (through a view)" picker implies the workflow in which this tool is used, giving agents an inferred usage context. However, there is no explicit when-to-use or when-not-to-use guidance and no named alternative among the many column/table listing siblings, so the agent must infer the routing itself.

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