search_columns

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

With no annotations, the description carries the full burden. It discloses search logic (OR, space-separated), return of table_name when omitted, and required params. However, it does not state whether the tool is read-only or describe pagination behavior for limit/offset, which are minor gaps.

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 extremely concise, using two sentences to cover purpose, required params, and two usage modes. No redundancy or filler.

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 an output schema present, return values need not be described. The description covers the core parameters (3 of 5) well, but omits limit/offset. Given the complexity of 5 params and 0% schema coverage, the description is mostly complete but has a minor gap.

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 must compensate. It explains keywords, schema_name, and table_name well, but fails to describe limit and offset parameters. Since limit and offset are common but not self-explanatory in context, this leaves a gap.

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 clearly states the tool searches columns by keywords (space-separated, OR logic) over name and comment, with a required schema_name and optional table_name. It effectively distinguishes from sibling tools like search_tables and search_schemas by specifying the resource (columns) and the two usage modes.

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 provides explicit guidance on when to use table_name (routine drill-down) and when to omit it (cross-table FK/JOIN-key reconnaissance). However, it does not mention alternatives like list_columns or execute_sql, leaving some ambiguity for edge cases.

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