Skip to main content
Glama

面灵AI 面试助手

start_exam

Destructive

在用户电脑上开始一场笔试,与桌面客户端笔试页点击「开始笔试」完全相同:按所给的答题模式、考试平台、岗位开场,打开笔试浮窗并收起主窗口(平台需要或用户在设置中开启时为原生笔试窗口)。需要用户电脑上的桌面客户端已登录并在运行;客户端不在线、版本较旧、额度不足、已有面试或笔试在进行时如实返回原因,不会开始。开始本身不扣费,之后每次截图答题按所选模式扣用户的时长。开始后用户在考试页面上照常使用浮窗截图答题;也可用 solve_screen_question 截屏解题。笔试记录在第一次截图答题时创建,之后可用 list_exams 查看。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

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "start_exam"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNo答题模式:instant = 秒答模式(每张截图 2 分钟);quick = 快速模式(每张截图 2 分钟);programming = 编程模式(每题 5 分钟)。会员不扣时长。不传 = 用户在客户端笔试页当前选择的模式
goalIdNo绑定的岗位 ID,取自 list_interview_targets;传 null = 不绑定岗位。与 jobName 二选一,都不传 = 沿用客户端笔试页当前填写的岗位
jobNameNo新岗位名称:用户没有保存过该岗位时填写,开始时当场创建(与在笔试页直接输入岗位相同)
platformNo考试平台名称(如「牛客」「北森」「赛码」「华为时习知」「国考云」「易考锁屏客户端」),不在客户端名录中的平台照用户的说法填写;少数平台会自动打开所需的截图方式。传 null = 不指定平台,不传 = 沿用客户端笔试页当前选择
companyNameNo新岗位的公司名称,与 jobName 一起填写

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Goes far past the annotations: it discloses the window choreography (floating window opens, main window collapses, native window for some platforms), when the billing clock actually starts versus what is free, that the exam record is only created at the first screenshot answer, and the authorization scope interviews:write. The destructiveHint=true annotation is consistent with the disclosed consumption of user time and state changes.

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?

Purpose and the client-equivalence anchor are front-loaded, and the dense single paragraph still proceeds logically from behavior to preconditions to billing to consent. The billing point is however made twice ('开始本身不扣费,之后每次截图答题…扣时长' and '会消耗用户的时长、次数或产生付款'), which is redundant bulk in an already long block.

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?

With no output schema, the description still tells the agent what to expect after a successful call (floating window active, record created only at first answer, visible via list_exams) and what a refusal looks like (a returned reason, no start). For a stateful, billable action this covers everything needed to call it responsibly.

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 100%, so the schema already documents mode, goalId/jobName exclusivity, platform examples, and the 'omit = inherit client-side selection' semantics. The description only broadly echoes that the mode, platform and job are supplied to the open call, adding no format or edge-case detail beyond the schema, so the baseline applies.

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?

Opens with a concrete verb+resource (开始一场笔试) and immediately anchors it to a known user action: identical to clicking 「开始笔试」 in the desktop client. It also names what it is not — the answering flow belongs to the floating window or solve_screen_question, and the resulting record surfaces via list_exams — so an agent can separate it from siblings without reading their schemas.

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?

States explicit preconditions (desktop client logged in and running) and enumerates the conditions under which it will refuse rather than start: client offline, outdated version, insufficient quota, or an exam/interview already in progress. It routes the agent to solve_screen_question for answering and list_exams for follow-up viewing, and adds a consent gate 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