get_schema

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

With no annotations, the description carries the burden of disclosing behavior. It explicitly states the output content (column names, types, nullability) and that the input must be an exact name from list_datasets. The read-only nature is implied by 'Get', and no side effects or permission requirements are mentioned, but for a metadata read this is acceptable.

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: two sentences plus a brief Args section. Every sentence contributes value, and the front-loaded purpose statement ensures immediate understanding.

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 simple one-parameter read-only tool, the description provides the essential information: purpose, input requirement, and prerequisite. No output schema is needed because the return type is described as column names, types, and nullability, which fully specifies the result expected.

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 schema provides only a string parameter with no description. The tool description fully compensates by explaining that 'dataset' must be the exact table or view name returned from list_datasets, and that it is required. This gives the agent precise guidance on how to populate the parameter.

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's function: retrieving column names, types, and nullability for a single dataset. It distinguishes this from sibling tools like list_datasets (which lists available datasets) and get_row_count (which counts rows), and specifies both tables and views are covered.

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 instruction 'Use list_datasets first to get valid names' provides a clear prerequisite and sequence of use. It does not explicitly list when not to use the tool, but the context of sibling tools makes the alternative use cases clear.

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