Skip to main content
Glama

面灵AI 面试助手

follow_up_screen_question

Destructive

对用户页面上当前这道截图题追问一句(如「换一种解法」「解释第 3 行」),与在页面上输入追问相同;AI 正在作答时不能追问。笔试追问按档位计费。执行端:用户正在进行笔试时为桌面客户端的笔试浮窗(需已开始本场笔试);否则为进行中的实时面试 / 模拟面试页面里的截图答题(网页端需已共享屏幕)。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": {
      "message": "<message>"
    },
    "name": "follow_up_screen_question"
  }
}

Input Schema

NameRequiredDescriptionDefault
messageYes追问内容

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

The description discloses behavior that annotations do not cover: the prerequisites about exam start and screen sharing, the billing tiers for exam follow-ups, the warning that user time, quota, or payment is consumed, the required consent step before execution, and the authorization scope interviews:write. The destructiveHint=true annotation is consistent with the disclosed cost and consent flow rather than contradicted. It only lacks a disclosure of what happens after a follow-up, for example, whether it replaces the prior answer.

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 purpose, followed by timing, endpoint routing, and billing and consent. It is dense but mostly earns its length. The endpoint-routing clause is long and nested, and it slows down scanning below the key purpose statement.

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?

Given a mutating, paid, state-dependent tool with no output schema, the description covers preconditions, cost, consent, authorization scope, and where the tool executes. There is nothing material an agent needs in order to invoke it correctly that is left out.

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?

There is a single parameter with 100% schema description coverage, so the schema already covers its meaning. The description still adds meaning by showing what a 'message' looks like (switching to another solution, explaining line 3), which helps the agent format a valid follow-up rather than a full question.

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 names a specific verb and resource in Chinese ("对用户页面上当前这道截图题追问一句"), gives concrete examples of the follow-up (「换一种解法」「解释第 3 行」), and draws a clear line between this tool and solving the question, so an agent can tell it apart from solve_screen_question 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 Guidelines5/5

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

The description states exactly when the tool applies, depending on the client and the user state: in a written exam, the follow-up runs in the desktop exam floating window and requires that this exam session has already started; otherwise it runs in the screenshot answering for an ongoing live interview or mock interview page, which requires screen sharing on the web. It also states the negative condition: no follow-up while the AI is answering. No alternatives are needed, and none are left to inference.

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