Skip to main content
Glama

面灵AI 面试助手

start_question_prediction

Destructive

为用户的目标岗位发起一次题库定制(押题):检索真实题库并结合简历,生成近期高频题与作答思路。发起后在后台生成,约 2–5 分钟,立即返回记录 ID;之后用 get_question_prediction 查看进度与结果,状态为 done 才算完成。非 PRO 用户生成成功后扣 1 次押题次数(失败不扣),PRO 用户占用本周 5 次额度中的 1 次(失败退回)。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": {
      "goalId": "<goalId>"
    },
    "name": "start_question_prediction"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNo输出语言的英文名,如 Simplified Chinese、English;不传按用户界面语言
goalIdYes目标岗位 ID
resumeIdNo简历 ID,取自 list_resumes;不传则只按岗位出题
experienceNo经验水平:应届生 / 1-3 年经验 / 3-5 年经验 / 5-10 年经验 / 10 年以上

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations only flag destructiveHint=true; the description supplies the details that make that flag meaningful. It states the run is asynchronous, takes 2–5 minutes, and immediately returns a record ID, and it spells out the billing rules: non-PRO deducts one 押题 credit, PRO consumes one of five weekly slots, and both refund on failure. It also names the required auth scope interviews:write and the consent obligation, all of which the annotations do not cover.

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 purpose, asynchronous behavior, and follow-up tool come first, and the billing and consent details come last. Every clause carries information, though the billing sentence is dense with parentheses and could be split for readability.

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 charging, asynchronous job-start tool with no output schema, the description covers everything an agent needs: that the return is a record ID, how long generation takes, which tool polls for results, what completion looks like, and what the call costs. Nothing material is missing.

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 goalId, resumeId, lang, and experience are already documented in the input schema. The description adds only a small amount of meaning beyond that: it notes that the resume is combined with the question bank, which implies how resumeId is used, but it adds no format or constraint detail beyond what the schema provides. The baseline 3 is appropriate.

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: 发起一次题库定制(押题), then says what it produces (检索真实题库并结合简历,生成近期高频题与作答思路). It also distinguishes itself from the sibling get_question_prediction, which only polls results, so an agent can tell the two apart without opening either schema.

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?

It gives clear usage context: call this for a 目标岗位, then poll with get_question_prediction and treat the job as finished only when status is done. It also adds a gating rule: before calling, explain the charge to the user and get consent. It does not state explicit when-not-to-use cases, such as re-starting an in-progress prediction, so it falls short of a 5.

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