Skip to main content
Glama

Start a worker session

agent_start

Start a reverse engineering session by configuring a worker model, optionally navigating to a target URL, and initiating AI-assisted analysis. Returns a session ID (tid) for subsequent tool calls.

Instructions

开一个新的逆向会话:配置 worker 模型(默认沿用浏览器里已配的)+关掉工具确认门、(可选)导航到目标 URL、建工作目录、用便宜的 worker 模型以【AI 辅助模式】发出第一轮(task 作为第 0 条 user)。返回 tid,后续都用它。绝不读/写 worker 的 key——key 由用户预先在浏览器里配好;这里只校验 hasKey=true。worker 选标准/快档别选推理档(推理档在长工具循环里易漂移成纯文字),如 deepseek-v4-flash / qwen-turbo / glm。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
taskYes逆向目标(成为 convo[0] 的 user 内容),例如:还原 xxx.com 的 X-S 签名并 Node 实打接口
targetUrlNo开跑前把当前 tab 导航到这个 URL
providerNo切到这个 provider 再跑(如 deepseek/zhipu/custom),省略=沿用浏览器当前 active。不碰 key,只校验该 provider 的 hasKey
modelNoworker 模型名(省略=沿用浏览器配置)。flash 档,如 deepseek-v4-flash(中转)/deepseek-chat(直连)
workspaceRootNo工作目录绝对路径(省略=在 FRX_WORKSPACE_ROOT 下自动建一个)
maxRoundsNo单轮最大工具回合,默认 80
assistNo默认 true=阶段门停。false=全自动
ensureConfirmOffNo默认 true=关掉工具确认门(无人值守必需)
Behavior4/5

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

With no annotations, the description fully discloses behaviors: does not read/write keys, creates workspace, navigates, checks hasKey, uses AI-assisted mode, returns tid. It also warns about reasoning model drift. Sufficient transparency.

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 dense and front-loaded with purpose, followed by detailed parameter guidance. It is not overly verbose, but could be slightly more streamlined. Still efficient given the complexity.

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

Completeness5/5

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

Despite no output schema, the description covers key return value (tid), session creation, configuration, URL navigation, workspace setup, model restrictions, and confirmation settings. Comprehensive for a complex tool.

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?

All 8 parameters have schema descriptions (100% coverage), but the tool description adds significant extra meaning: model must be flash tier, avoid reasoning models; ensureConfirmOff default true needed for unattended; assist default true; workspaceRoot defaults to FRX_WORKSPACE_ROOT. Adds substantial value beyond schema.

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 starts a new reverse session, configures worker model, turns off tool confirmation, optionally navigates to URL, creates workspace, and sends first round. It distinguishes from siblings by being the startup action.

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 specific guidance on when to use, including model selection (avoid reasoning models), key handling (never read/write), and requiring ensureConfirmOff=true for unattended use. However, it does not explicitly list when not to use or compare to siblings.

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/WhiteNightShadow/frx-director-mcp'

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