List the distinct sections of a page (hero, pricing cards, testimonial/feedback, footer, ...) so you can emulate a specific part. Each section links back to its page (parent_slug) and the product's design system (call get_design_system(site)).
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden. It discloses that each section links back to its parent page and the design system, giving useful context about the returned data. It does not mention pagination, filtering, or mutability, but for a read-only listing tool this is moderately transparent.
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 sentences, front-loads the core action with examples, and adds relevant navigation context. No wasted words.
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 tool's simplicity (one parameter, no output schema, no annotations), the description adequately covers what it does and what the results contain. It could mention the return format or that it returns an array, but the examples and links to related tools make it sufficiently complete for an agent to select and invoke.
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 has 0% coverage for the single 'slug' parameter. The description implies slug identifies the page ('of a page'), which helps, but it doesn't explicitly define what a valid slug looks like or how it relates to parent_slug. It adds some meaning but does not fully compensate for the missing schema documentation.
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's function: to list distinct sections of a page, with concrete examples (hero, pricing cards, footer). It also distinguishes itself from related tools like get_screen (page-level) and get_section (specific section) by focusing on enumerating sections.
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 explains the intended use case ('so you can emulate a specific part') and points to get_design_system for design system context. It could be clearer about when to use this instead of get_section, but the purpose is well implied by the examples and structure.
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.
The compare_* / get_* / search_* family creates real overlap: compare_components, get_component, get_recipe, and search_screens(kind="component") can all answer similar component questions, and the drift family (get_design_drift, get_design_history, list_design_changes) requires careful reading to pick the right one. However, the detailed descriptions mostly draw clear lines between cross-product comparison, single-spec retrieval, and corpus-level search.
The server mostly follows a clean verb_noun convention: get_*, compare_*, list_*, search_*, validate_design, generate_asset. The pattern is highly consistent, though a few names differ slightly in style (audit_code vs validate_design vs get_score), and pluralization varies in tools like compare_components and compare_sections.
At 23 tools this is on the heavy side, and several calls overlap in scope enough to feel redundant. That said, the server's broad purpose suggests a design system reference plus audit platform, so the count is justifiable; it could be consolidated into a tighter 15-18 set.
The surface covers design system retrieval, component/section/recipe specs, screens and flows, search, audit/tools, icon assets, and drift/history of measured design tokens, leaving few cap gaps for the declared domain. Minor gaps remain around some metadata like direct screenshot banding by product, but no major dead-end workflow is apparent.
