Skip to main content
Glama
huaka1
by huaka1

browser_export_steps

Export buffered browser actions as JSONL test cases with saved login state for regression testing.

Instructions

把缓冲区的页面操作步骤导出成 jsonl 测试用例,同时保存登录态。

导出后清空缓冲区。以后回归时:让 agent Read 这个 jsonl, 用 browser state load 加载 auth.json,按步骤用 browser_navigate/click/type 重放 (用 role+name 定位,不用 ref),看当下 url/title 跟录制时一不一致自己判断对错。

Args: name: 用例名,文件名为 test_{name}.jsonl domain: 领域名(如 auth/task/file/cron/skill),作为子目录名 from_step: 从第几步开始导出(1-based),默认 1=全部。用 browser_list_steps 看编号后决定。 session_id: Browser session ID(用于保存登录态)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYes
domainYes
from_stepNo
session_idNodefault

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

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

The description discloses key behaviors beyond the schema: it empties the buffer after export ('清空缓冲区'), saves login state, and ties session_id to auth. This is critical for a tool that modifies state, and no annotations are present to contradict.

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 front-loaded with the core purpose, then explains the workflow, and finally lists parameters. It is reasonably concise for the complexity, though the parameter documentation could be more structured (e.g., bullet points).

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 existence of an output schema (though not visible), the description covers the essential context: export format, buffer clearing, and usage in regression. However, it doesn't specify the return value (e.g., file path) or detail how the session_id saves login state.

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

Parameters5/5

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

With 0% schema description coverage, the description fully compensates by explaining each parameter: name (test case name), domain (subdirectory), from_step (starting step, default 1), and session_id (for login state). This provides clear meaning beyond the schema's type-only definitions.

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 that the tool exports page operation steps from buffer to jsonl test cases and saves login state. It distinguishes from siblings like browser_list_steps (which lists steps) by focusing on export and clearing buffer.

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 provides a detailed regression workflow, referencing sibling tools (browser_list_steps for step numbering, browser_navigate/click/type for replay). However, it doesn't explicitly state when not to use this tool or give direct comparisons to alternatives.

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/huaka1/browser-mcp'

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