Validate and optionally save a custom component for the authenticated tenant. Runs review_generated_code validation before persisting. Use for AI-generated or customized components.
| Name | Required | Description | Default |
|---|---|---|---|
| code | Yes | Generated TSX code using @marmoui/ui primitives | |
| save | No | Save as tenant component override if validation passes | |
| description | Yes | What the component should do | |
| componentName | Yes | PascalCase component name, e.g. CustomStatCard |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the transparency burden. It discloses the validation step and optional saving, but it does not state what happens on validation failure, the return format, or any permission requirements. This is a partial gap for a mutation tool.
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 sentences, front-loaded with verb and resource, no redundant wording. Every sentence earns its place: one for purpose, one for workflow and use case.
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 absence of an output schema and annotations, the description covers the core purpose, workflow, and use case well. It could mention return values or failure behavior, but the essential context is present.
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 the baseline is 3. The description does not add any parameter-specific meaning beyond what the schema already provides; it focuses on the workflow rather than parameter details.
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 the tool validates and optionally saves a custom component for the authenticated tenant. It specifically mentions running review_generated_code validation before persisting, which distinguishes it from sibling tools like review_generated_code that only validate.
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 explicitly says 'Use for AI-generated or customized components,' providing clear context. It also describes the validation-before-persist workflow, which implies a contrast with validation-only tools, though it does not name an alternative directly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have distinct purposes, but there is some overlap between review_generated_code and validate_component_usage, and between list_components and search_components. However, descriptions clearly differentiate their intended use cases, reducing ambiguity.
All tools follow a consistent verb_noun pattern with snake_case (e.g., get_component_info, generate_component, review_generated_code). The naming is predictable and clearly indicates the action.
14 tools is well-scoped for a UI design system assistant. It covers component discovery, detailed info, design guidelines, theme, code generation and validation, and prototype management without being overwhelming.
The tool set covers the full workflow: discover components, get patterns, get design guidelines, generate and validate code, get tenant theme, deploy prototypes and collect feedback. No obvious gaps for the intended usage scenario.