get_reference

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

No annotations are present, so the description carries the full burden. It conveys a read-only get operation and the returned data, but does not describe edge cases (invalid/missing table_id), permissions, or potential failure modes. The behavior is nonetheless simple and predictable.

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 sentences, with the operation and return fields front-loaded in the first sentence and the workflow directive in the second. Every word earns its place.

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 one-parameter getter without an output schema, the description covers the operation, the return contents, and the invocation timing. It does not address error behavior or distinguish from the lookup sibling, but this is a minor gap for such a simple tool.

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 only lists 'table_id' with no description, leaving 0% schema coverage. The description refers to 'a lookup table' and instructs calling after search_lookups, which implies table_id comes from those search results, but it never explicitly defines the parameter's source or format. This partially compensates for the missing schema detail.

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 uses the verb 'Get' with a specific resource ('a lookup table') and lists the exact return fields ('purpose, keys, notes'). This clearly differentiates it from siblings like search_lookups, which searches, or lookup, which likely performs a lookup against the table.

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 explicit instruction 'Call after search_lookups' provides a clear workflow context, telling the agent this tool should be used subsequent to a lookup search. It does not mention alternatives or exclusions, but the sequencing guidance is unambiguous.

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