get_reference_data

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

With no annotations provided, the description fully discloses important behavior: auto-pagination, the default 10-row truncation footgun, and the full list return with a 'returned' count. This is highly transparent and warns about a subtle issue.

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 front-loaded with the purpose and then delves into auto-pagination. Each sentence adds value, but the second paragraph is somewhat lengthy. Could be slightly more concise without losing critical warnings.

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 single parameter, no output schema, and the complexity of auto-pagination behavior, the description is complete. It explains the return envelope, the pagination issue, and the key reference source, fully covering what an agent needs.

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?

There is only one parameter ('key') with a schema description that directs to list_query_object_types for valid keys. The description adds value by referencing the source of allowed values, going beyond the schema's basic description.

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 fetches reference/lookup lists, provides concrete examples (contact types, tags), and specifies it is read-only. It distinguishes itself from siblings by focusing on reference data 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 indicates it is used to 'build queries or understand allowed values,' which provides clear context. However, it lacks explicit guidance on when not to use this tool versus alternatives, such as get_query_options or list_query_object_types.

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