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

The annotations already establish read-only, idempotent, non-destructive behavior. The description adds useful behavioral context by defining the return shape (an index of id, label, macrostructure, note) and clarifying that this tool does not return source code, which is a separate call.

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 two tight sentences with no filler. It front-loads the tool's purpose and output fields, then immediately gives the follow-up action, making every sentence earn 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 simple read-only index tool with optional filters, the description plus schema cover the invocation and return shape well. The only minor gap is the lack of explicit statement about default behavior when no parameters are provided, though the schema does mention 'Omit to scan all types'.

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 description coverage is 100%, so both parameters are already documented. The description reinforces the macro concept and category context but does not add meaningful parameter-level detail beyond what the input schema provides, so the baseline 3 is appropriate.

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 names a specific resource ('canonical reference components'), states that it returns an index with id, label, macrostructure, and note, and lists the archetype categories. It differentiates itself from get_reference_jsx by explicitly saying that tool provides the source, so an agent can tell the two apart.

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 gives a clear usage flow: pick a reference component from this index, then call get_reference_jsx(type, id) for the source. It does not explicitly enumerate exclusion criteria or contrast with other siblings like find_components, but the intended workflow is unambiguous.

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