Skip to main content
Glama

studio_review_design

Capture screenshots and machine checks for a Studio page revision, return images for visual inspection, submit observations with reviewId, and compare prior reviews to see before-and-after changes.

Instructions

为当前版本创建真实截图和机器检查,返回图片供模型看图;用 reviewId 提交具体 observations。旧版本拒收。compareWithReviewId 可返回前后两张图及变更区域。评审不调用额外模型、不自评审美分、不代表用户验收。

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "pageId": "<pageId>",
      "baseRevision": "<baseRevision>"
    },
    "name": "studio_review_design"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNo
portNo
pageIdYes
verboseNo默认摘要;true返回完整指标和节点快照
reviewIdNo
projectDirNo
baseRevisionYes
observationsNo
compareWithReviewIdNo同页此前评审 ID,返回前后两张真实图片、变更节点范围和指标变化

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.4.5

TDQS

A3.8/5.0
Behavior4/5

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

The annotations only declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, so the extra behavioral detail here is valuable: the review does not invoke additional models, does not self-score on aesthetics, and does not constitute user acceptance sign-off. It also discloses that old revisions are rejected. It does not cover side effects on disk or how the review state persists, which would be the final piece.

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 text is a compact, semicolon-delimited block that leads with the core action and then layers on constraints and the comparison option. Every clause carries information, and no sentence is filler. The density of unrelated facts packed into one run-on weakens scannability slightly.

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 9-parameter tool with no output schema and thin annotations, the description should more fully describe the inputs and what comes back beyond 'images'. It does well on scope and review semantics, but an agent still cannot tell what url, port, or projectDir are for, or what the machine-check results look like.

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 only 22% across 9 parameters, so the description has to carry real weight. It does explain reviewId (submits observations), observations (concrete findings to report), and compareWithReviewId (returns before and after images plus changed regions). But url, port, projectDir, and verbose get no meaning from the description at all, leaving roughly half the surface undocumented.

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 uses a concrete verb and resource: create real screenshots and machine checks for the current revision, and return the images for the model to view. It also states a second phase: submit observations via reviewId. The purpose is unambiguous, but nothing in the text separates this tool from the sibling studio_capture_screenshot, so an agent must infer the difference from the name alone.

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

Usage Guidelines4/5

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

The description spells out a usable workflow: first generate the screenshots and checks, then attach specific observations using reviewId, and reject stale revisions. The compareWithReviewId branch is conditional and clearly stated. It lacks explicit when-not guidance versus sibling capture and metrics tools, which keeps it out of the top band.

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