list_columns

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

No annotations are provided, so the description must disclose behavioral traits. It states the operation is a read ('List') but does not explicitly confirm read-only safety, mention any side effects, permissions, rate limits, pagination, or return format. The agent is left guessing about response structure and any constraints, which is a significant gap for a tool with no structured annotations.

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 a single sentence with no wasted words. It front-loads the core action and immediately notes the optional search capability. It is concise, though the brevity sacrifices necessary detail; still, for what it conveys, it is well-structured.

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 list operation with three parameters and no output schema, the description is underspecified. It lacks return format, pagination behavior, sorting, any constraints on the search query, and does not clarify the roles of the two required parameters. Sibling tools like search_columns and get_column exist, but the description offers no context to distinguish use cases, leaving the agent with insufficient information to use 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 0%, so the description must explain all parameters. It only addresses the optional 'query' via 'Optional text search', leaving 'model_id' and 'table_ref' entirely unexplained. Without knowing what these identifiers refer to (e.g., model UUID, table reference format), the agent cannot correctly invoke the tool.

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 action ('List columns of a table') and mentions 'full attributes' and 'optional text search', which distinguishes it from single-column retrieval (get_column) and broader searches (search_columns). However, it does not explicitly name sibling alternatives or specify the scope beyond the table, so it lacks the sharpest differentiation.

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?

There is no guidance on when to use this tool versus alternatives like get_column or search_columns. No mention of prerequisites (e.g., model must be open), no exclusion cases, and no indication of when text search is appropriate. The description implies a straightforward listing but does not help the agent decide between this and sibling tools.

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