Skip to main content
Glama

studio_design_metrics

Read-only

Computes page visual-completion metrics—type scale, 4px grid consistency, whitespace, text contrast, hue count—plus anti AI-slop rule checks, returning reproducible structural findings and concrete fixes.

Instructions

计算页面的 L1 视觉完成度代理指标(字阶比、4px 栅格一致性、留白占比、文本对比度、主色相数)与反 AI-slop 负样本规则(等距三卡、紫渐变、空洞居中标题、图标圆角方块、首屏无素材、圆角过度)。每条 slop 规则的触发阈值随结果 slopRules 返回——未命中可能只是样本低于阈值,不代表规则失效。不返回审美总分:只给可复现的结构判断与具体改法。

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": "studio_design_metrics"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNo
portNo
pageIdNo
pixelTruthNo默认真实浏览器像素测量;false 显式使用几何估算。失败回落时标注原因。
projectDirNo
thresholdsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.4.5

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds genuinely useful behavior beyond that: thresholds are surfaced under slopRules, and a non-trigger may just mean the sample is below threshold rather than the rule being broken — a non-obvious caveat worth stating. It still doesn't describe cost, runtime, or failure modes beyond what the pixelTruth parameter already documents.

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?

Three sentences, front-loaded with what is computed and what is returned, with no filler. The threshold-caveat sentence is long but earns its place because it prevents a misreading of results.

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 read-only measurement tool with no output schema, the description covers purpose and the shape of the slopRules results reasonably well. It is still incomplete about how to invoke it correctly — target selection among url/pageId/projectDir and threshold overriding are undocumented, which matters for a 6-parameter tool.

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

Parameters2/5

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

With 6 parameters and only 17% schema description coverage, the description must compensate, but it never explains url, port, pageId, projectDir, or the nested thresholds object — in fact thresholds is only referenced as an output concept (slopRules), not as an overridable input. An agent cannot tell from the description whether url or pageId is the primary target or how to override trigger thresholds.

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 first sentence names a specific verb (computes) and resource (L1 visual-completion proxy metrics) and enumerates the exact metrics and slop rules measured, which is far more concrete than a generic 'analyze design' description. It does not name a sibling such as studio_design_pixel_contrast or studio_review_design, so an agent must infer the boundary from the metric list alone.

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?

Usage is implied — you run this to get structural visual-quality measurements for a page — and the scope limit (no aesthetic score, only reproducible structural judgments) is helpful. However, there is no explicit when-to-use/when-not, no mention of prerequisites or how it relates to the fix-plan or review siblings.

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

Deploy Server

Other Tools