describe_table

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

No annotations are present, so the description carries the burden. It mentions an error condition for schema allowlisting but does not explicitly state read-only behavior, response format beyond 'column metadata', or handling of non-existent tables. Adequate but lacking depth.

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 sentences. First sentence efficiently states the purpose; second adds a key constraint. No extraneous text. Front-loaded with the core action.

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?

Given the simple nature of the tool (returning column metadata) and presence of an output schema, the description covers the essential: what it does and a notable error condition. It could mention that results are read-only or that it describes exactly what columns exist, but overall sufficient.

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?

Input schema has 0% property description coverage. The description uses 'SCHEMA.TABLE' to imply a dot-separated usage pattern but does not specify case sensitivity, allowed characters, or format conventions. Minimal value added beyond the schema's 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?

Description explicitly states 'Return column metadata for SCHEMA.TABLE', which clearly identifies the action (return) and resource (column metadata) for a specific schema and table. It distinguishes from sibling tools like list_schemas or run_select by implying DDL metadata retrieval.

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 a constraint ('Errors if schema is not in the configured allowlist') but does not explicitly guide when to use this tool over siblings (e.g., vs list_schemas for schema listing or run_select for data). Usage context is implied but not explicit.

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