Skip to main content
Glama

Lazynext AI Slop Checker

scan_render

Run the rendered-tier design checks (r-*): kicker size, gradient text, tracked caps, glued arrows, marquee, hidden reveal, fold budget, screen word budget, section rhythm, fake progress, and WCAG contrast — all pure functions over a computed snapshot ({elements:[...]}, see src/render-checks.js). Pass an object snapshot; no browser needed.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "scan_render"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNohttp(s) URL to collect then check (requires the optional playwright collector)
profileNoseverity profile (default | strict | lenient)
snapshotNocomputed snapshot: { viewport?, documentStyle?, elements: [...], screens? }

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description carries the full disclosure burden, and it does contribute meaningful facts: the checks are pure functions over a snapshot, no browser is needed for the snapshot path, and the playwright collector is an optional dependency for the url path. It stops short of describing what is returned (findings list, severity handling from the profile) or how the three mutually-exclusive-ish inputs interact.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The verb and resource are front-loaded, and the long check enumeration earns its place by letting an agent match a request ('WCAG contrast', 'fold budget') to this tool. The closing input sentence is efficient; the check list is the only slightly heavy portion, and it is functional rather than filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a check-runner with no annotations and no output schema, the definition should ideally explain the result shape and precedence among url/snapshot/profile. It covers the snapshot contract by reference but leaves the all-optional parameter set ambiguous (what runs with zero args?) — adequate, with a clear gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents url, profile, and snapshot, setting the baseline at 3. The description adds modest value — pointing to src/render-checks.js for the expected snapshot shape and noting the playwright requirement — but adds nothing about the severity profiles or the interaction between mutually exclusive inputs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific action and resource — running the 'rendered-tier design checks (r-*)' — and enumerates the actual check families (kicker size, gradient text, WCAG contrast, etc.), so an agent knows precisely what it evaluates. It distinguishes itself from the html/text/project scanners only implicitly via 'rendered-tier' and 'computed snapshot' rather than naming a sibling, keeping it just short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives input-mode guidance ('Pass an object snapshot; no browser needed'; url 'requires the optional playwright collector'), which implies this tool is for pre-computed DOM snapshots rather than raw sources. However, it never states when to prefer scan_html/scan_text/scan_project over this, nor what happens when no argument is supplied despite zero required parameters — usage must be inferred.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.