Skip to main content
Glama

面灵AI 面试助手

start_interview

Destructive

为用户发起一场实时面试或模拟面试,返回面试页链接,由用户在浏览器打开(仅支持网页版,不调起桌面客户端;用户需在浏览器登录同一账号)。实时面试:用户在面试页按提示共享带声音的会议标签页,点击「开始面试」后按在线时长扣面试时长;模拟面试:创建时预扣 1 次模拟面试次数。同一类型同时只能有一场进行中。未指定的高级配置(回答风格、自定义要求、翻译、复盘录音、联网搜索、知识库)沿用用户在网页端保存的面试偏好。岗位 ID 取自 list_interview_targets,简历 ID 取自 list_resumes。会消耗用户的时长、次数或产生付款,执行前向用户说明扣费内容并取得同意。(需要用户授权,范围 interviews:write)

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": {
      "targetId": "<targetId>",
      "resumeId": "<resumeId>"
    },
    "name": "start_interview"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNo面试语言(决定语音识别模型);不传 = 用户偏好中的语言
modeNo仅实时面试:online = 线上面试(采集会议声音),phone = 电话面试(手机免提外放、麦克风采集,需已注册声纹,仅中文 / 粤语 / 英语)online
typeNoINTERVIEW = 实时面试,MOCK_INTERVIEW = 模拟面试INTERVIEW
focusNo仅模拟面试:本场主攻方向
roundNo仅实时面试:本场是该岗位第几轮
resumeIdYes简历 ID
targetIdYes岗位 ID
skipIntroNo仅模拟面试:跳过自我介绍
assistModeNo仅模拟面试:是否开启 AI 辅助(每道题给出参考回答)
difficultyNo仅模拟面试:难度(工作年限)FRESH_GRADUATE
extraLangsNo仅实时面试:面试中还可切换到的其他语言;不传 = 用户偏好
basicsRatioNo仅模拟面试:基础知识题占比 0–100;不传 = AI 自行安排
questionCountNo仅模拟面试:题量;不传 = AI 自行安排
knowledgeBaseIdsNo知识库 ID 列表;实时面试不传 = 用户偏好中选中的知识库,模拟面试仅在开启 AI 辅助时生效

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the destructiveHint=true annotation, the description discloses the actual cost mechanics: real-time interviews deduct time based on online duration, mock interviews pre-deduct one mock-interview credit, and payment may be generated. It also states the auth scope (interviews:write) and that unspecified advanced settings inherit the user's saved web preferences, which the annotations cannot convey.

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 most decision-relevant facts (what it does, browser-only, link returned) are front-loaded, and the dense single paragraph contains essentially no filler. It loses a point for being a wall of text with no separation between mode rules, billing, and ID sourcing, which makes scanning harder than necessary.

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?

For a 14-parameter, destructive, billing-relevant tool with no output schema, the description covers everything an agent needs: return value (interview page link), auth scope, concurrency limits, cost model, ID provenance, and default-inheritance behavior. Nothing material is left to inference.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3; the description earns an extra point by explaining that any omitted advanced configuration (answer style, custom requirements, translation, recording, web search, knowledge base) falls back to the user's saved web preferences. It does not restate the per-parameter enum semantics, which the schema already handles well.

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 opens with a specific verb and resource: launch a real-time interview or mock interview and return a browser-opened interview page link. It immediately splits the two modes (INTERVIEW vs MOCK_INTERVIEW), which lets an agent distinguish this from session-control siblings like answer_live_interview_now or end_live_interview without opening the schema.

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

Usage Guidelines5/5

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

Explicit preconditions and routing are given: web only, no desktop client, the user must be logged into the same account in the browser, and only one session of a given type may run concurrently. It also names the source tools for required IDs (list_interview_targets for targetId, list_resumes for resumeId) and mandates explaining charges and obtaining consent before execution.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources