describe_table

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

Describes return format comprehensively. Lacks details on error handling (e.g., table not found) but covers the core behavior well. No annotations, so description carries full burden.

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 short paragraphs: purpose first, then args/returns. Every sentence is useful; no 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?

Single parameter adequately explained, return format specified, and reference to sibling tool. Complete for an agent to invoke 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 has no description for the 'table' parameter, but the description provides crucial guidance: exact name from list_tables, with examples. This compensates fully for the schema 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?

Clearly states it shows columns of a table with specific fields (name, type, nullability, key, default, extra). The verb 'show' and resource 'columns' are specific and distinguish it from siblings like list_tables.

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?

Points to list_tables to get exact table name, implying the correct workflow. Does not explicitly state when not to use, but context is clear enough.

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