describe_table

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

Describes caching behavior (first call queries Snowflake live, subsequent calls cached) and error conditions (table not in cache). Does not mention authorization or read-only nature explicitly, but overall disclosure is sufficient given no 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?

Well-organized into sections with clear headings: purpose, when-to-use, returns, how it works, parameters, examples. Every sentence adds value without unnecessary fluff.

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?

Covers key aspects: purpose, usage, behavior (caching, error), and prerequisites. Lacks explicit mention of output schema structure, but an output schema exists so this is less critical.

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?

The description lists all three parameters (database, schema, table) and provides examples with real names, clarifying their expected format despite the schema having no descriptions.

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 it provides detailed column information for a specific table. It uses specific verbs like 'Get' and explicitly distinguishes itself from siblings like execute_query and show_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?

Includes a 'USE THIS WHEN' section that tells when to use it (need column names, types, constraints). Also implicitly guides when not to use it by directing to execute_query for sample data and show_tables/find_tables for table discovery.

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