Skip to main content
Glama

browser_debug

Generate browser debug reports, diagnose error root causes, or investigate symptoms with automated evidence collection and hypothesis generation.

Instructions

浏览器调试诊断工具(v1.9.5 起合并 browser_debug_report/browser_diagnose/debug_investigate)。通过 mode 参数区分子模式:report(默认,生成调试报告汇总页面状态、错误日志、网络错误)/ diagnose(自动诊断浏览器错误根因,返回 rootCause/confidence/suggestedFixes)/ investigate(输入问题症状,自动汇总 errors/events/network/DOM/storage/artifacts 并输出假设和证据链)。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNo调试模式:report(默认,生成调试报告)/ diagnose(诊断错误根因)/ investigate(问题调查与假设)report
focusNo关注的 URL/API 关键字,例如 /api/ai/summarize(mode=investigate 时使用)
limitNo网络和事件最多返回条数,默认 20/50(mode=investigate 时使用)
symptomNo问题现象,例如:点击 AI 要点后 403(mode=investigate 时使用)
expectedNo期望结果,例如:生成 AI 要点(mode=investigate 时使用)
selectorNo目标元素选择器,诊断该元素相关的错误(mode=diagnose 时可选,不传则诊断整个页面)
errorTypeNo聚焦诊断的错误类型:all(全部)、js(JS错误)、network(网络错误)、element(元素问题)、interaction(交互失败),默认 all(mode=diagnose 时使用)all
statusMinNo只关注状态码大于等于该值的网络记录(mode=investigate 时使用)
includeDomNo是否包含页面文本和元素摘要,默认 true(mode=report 时使用)
urlContainsNofocus 的别名,按 URL 过滤网络和事件(mode=investigate 时使用)
includeStorageNo是否包含存储信息,默认 false(mode=report 时使用);mode=investigate 时默认 true
includeArtifactsNo是否包含 artifacts 列表,默认 true(mode=investigate 时使用)
includeStackTraceNo是否包含 JS 错误堆栈分析,默认 true(mode=diagnose 时使用)
Behavior4/5

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

With no annotations, the description carries full burden and details what each mode does and what it returns (e.g., rootCause, suggestedFixes, hypothesis chain). It does not mention prerequisites like requiring an active session.

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 description is a single dense paragraph that efficiently conveys the tool's purpose and modes without wasted words. It could be improved with bullet points for readability.

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

Completeness4/5

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

Given the tool's complexity (13 parameters, 3 modes), the description provides a good overview of modes and outputs. However, it does not explicitly map parameters to modes or detail return values comprehensively since no output schema exists.

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 coverage is 100%, so baseline is 3. The description adds context for the mode parameter but does not elaborate on each parameter beyond what the schema already provides.

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

Purpose5/5

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

The description clearly states the tool is a browser debug diagnostic tool with three specific sub-modes (report, diagnose, investigate) and mentions it merges three predecessor tools, distinguishing it from siblings.

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 explains when to use each sub-mode (e.g., generate report, diagnose errors, investigate symptoms) but does not explicitly exclude alternative sibling tools for more focused operations.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/validpilot/ai-verify-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server