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

Annotations already convey read-only, idempotent, non-destructive behavior. The description adds useful behavioral context by highlighting that results are real sites and that each result may include a per-element crop when one exists. It also positions this as an example-finding tool, not a code-generation tool. No contradiction with 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?

The description is compact: two sentences, front-loaded with the core purpose and followed by a useful routing note to a sibling. However, the long parenthetical enum list repeats the schema's type values, so it is not perfectly economical.

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 complex tool with 11 parameters and no output schema, the description provides only a high-level purpose and one sibling handoff. It does not clarify result shape, ranking behavior, how filters combine, or how this tool relates to the other close siblings like find_reference_components and search_screens. The schema compensates partially, but the description leaves meaningful gaps.

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 input schema already describes type, vibe, color, style, device, pageType, and maxTokens in some detail, covering 64% of parameters. The description does not add meaningful parameter semantics beyond listing the component types inline, which duplicates the type enum. Parameters like mode, limit, industry, and macrostructure are left to schema enums without additional context.

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 verb and resource: find real sites featuring a UI component, with a per-element crop where available. It also explicitly contrasts with get_reference_jsx. However, it does not differentiate itself from the similarly named sibling find_reference_components, leaving some ambiguity about which of those two to choose.

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 one clear usage rule: use get_reference_jsx when copy-pasteable code is needed instead. It also implies use for real-site examples with crops. It does not cover when to choose find_reference_components, find_by_color, or find_examples_for_macrostructure over this tool, so the guidance is partial rather than complete.

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