Find the right UI components by searching a curated registry with keyword, category, or tag filters.
Searches 21st.dev & curated high-craft UI component registry by keyword, category, or tag.
| Name | Required | Description | Default |
|---|---|---|---|
| tag | No | Specific tag e.g. 'glassmorphism', 'apple-hig', 'framer-motion' | |
| query | No | Search term e.g. 'glowing', 'dock', 'bento' | |
| category | No |
Changes observed during successful MCP inspections.
v1.8.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The wording 'Searches' indicates a non-mutating operation, and naming the registry gives useful context beyond the schema. However, with no annotations and no output schema, it does not disclose how results are returned, whether multiple filters combine, or any service limitations.
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?
A single, front-loaded sentence states the operation, resource, and search criteria without redundancy. Every clause contributes meaning, and there is no filler.
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 search tool with three optional parameters, the description covers the core purpose and source. It falls short by not explaining result behavior, parameter combination logic, or how this step relates to subsequent tool calls like get_component_code.
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 coverage is 67%, with tag and query having examples and category only having an enum. The description adds mild value by grouping all three fields as search dimensions, but it does not clarify whether parameters are mutually exclusive or combinable, nor does it describe category semantics.
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 uses a specific verb ('Searches'), names the resource ('21st.dev & curated high-craft UI component registry'), and lists the three search dimensions: keyword, category, or tag. It is clear and scoped, though it does not explicitly contrast itself with siblings like get_component_code.
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?
No guidance is given about when to choose this tool over alternatives, such as get_component_code for fetching a specific component's implementation. The description implies general search usage but does not state prerequisites, exclusions, or preferred sibling routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.