Score a public website 0 to 100 for the design habits that make it look AI-made.
Scored across 1 tool
There is only one tool, so there is no possibility of confusion or misselection. Its purpose (score a single URL for AI-slop design habits) is clearly bounded and distinct from anything else in the surface.
The single tool follows a clear snake_case verb_noun convention (slopscore_check_website). With one name there is no mixed-convention risk, and the name is readable and self-descriptive.
One tool is borderline thin; the domain (checking a URL for generic/AI-looking design) could reasonably support related operations like batch checking or retrieving a saved report. Still, the single tool earns its place and covers the core ask, so it is not a severe mismatch.
The tool returns a score, verdict, found habits with evidence and fixes, and unfound habits, which is a full result surface for the stated purpose. Minor gaps exist, such as no multi-URL/batch checking or persisted comparison across runs, but agents can work around these by calling it per URL.
Use when the user asks whether a website, landing page or app looks AI-generated or generic, wants a design critique of a live URL, or asks "does my site look like AI slop?". Fetches the page and checks 19 habits (purple-blue gradients, buzzword copy, glassmorphism, icon-card grids, template headlines, app-builder fingerprints and more), then returns a 0-100 score, a verdict, each habit found with the evidence and how to fix it, and the habits that were not found. It is a habit check, not an AI detector. Public http(s) pages only. Example: {"url": "https://example.com"}.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Public website address, for example example.com or https://example.com/pricing |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover readOnly/openWorld/idempotent/non-destructive, and the description adds real value on top: it fetches the page over the network, enumerates what is checked (19 habits), and describes the return payload (0-100 score, verdict, per-habit evidence and fix, plus not-found habits). It stops short of failure modes, timeouts, or whether JS-rendered pages work.
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?
Front-loaded with the trigger condition, then scope, then output shape, then example — a sound ordering. The 19-habit parenthetical list is dense but each item is evidence-bearing rather than 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 one-parameter, no-output-schema, read-only tool this is nearly complete: it covers when to call, what is fetched, what comes back, and the public-URL restriction. The only gap is edge behavior (unreachable page, JS-only rendering) that an agent might want before calling.
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 100% and the single url parameter is already documented with an example. The description's 'Public http(s) pages only' does add a genuine constraint on acceptable values beyond the schema, plus a concrete example invocation.
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?
States a specific verb (scores/checks) and resource (a live website/landing page/app) and explicitly bounds itself: "It is a habit check, not an AI detector." That negation lets an agent separate it from adjacent AI-detection tools without any sibling list.
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?
Opens with concrete trigger conditions ("Use when the user asks whether a website... looks AI-generated or generic") and includes a near-literal user phrasing ("does my site look like AI slop?"). It also states the exclusions/constraints: public http(s) pages only, and explicitly not an AI detector.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
slopscore_check_siteslopscore_check_websiteslopscore_check_siteDesign quality gate for AI-generated UI: score any URL on 45 deterministic checks, A–F grade.
Scores any public website on how usable it is by AI agents, with per-check evidence.
Score any website out of 100 for how well AI agents can find, understand and use it.
Scan a public website for AI agent readiness: 60 checks, a score, and the evidence for each.
Add one secure layer between your agents and this server.
