Skip to main content
Glama

面灵AI 面试助手

draw_interview_session

Read-only

从题库还原一场真实面试:抽取一篇面经中面试官按顺序追问的完整题目链(公司、岗位、月份、题目 ID 顺序即追问顺序)。该筛选条件下没有足够长的场次时如实返回「没有」,此时可改用 draw_questions 抽散题。

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": "draw_interview_session"
  }
}

Input Schema

NameRequiredDescriptionDefault
companyNo公司名
positionNo岗位,如「后端开发」「算法」
employmentTypeNo招聘类型,如「校招」「实习」「社招」
interviewRoundNo面试轮次,如「一面」「二面」「HR面」

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnly, non-destructive, closed-world, so the safety profile is covered. The description adds genuinely new behavior: the empty-result path is honest ("returns none" rather than fabricating a chain) and the returned chain is ordered by follow-up sequence. It does not describe shape or size of the returned payload (how many questions, what fields beyond company/position/month), which matters with no output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the core action, then the fallback. No restatement of the tool name, no marketing filler; every clause (ordering semantics, empty case, alternative tool) carries load-bearing information.

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

Completeness4/5

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

For a read-only tool with four optional filters, no output schema, and flat parameters, the description covers what it does, what ordering means, and what happens when nothing qualifies. It stops short of saying what an unfiltered call returns (any session? shortest acceptable chain?) and how large a returned chain typically is, both of which the agent would need to set expectations.

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% with per-parameter Chinese descriptions, so the baseline would be 3. The description adds a little: it frames the filters as the domain of a single real interview experience (company, position, month) and notes they jointly select one chain. Minor friction: it names 月份 (month) as a selecting dimension, but no month parameter exists in the schema, which could briefly confuse an agent mapping intent to arguments.

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?

States a specific verb and resource: reconstruct one real interview from the question bank by extracting the interviewer's ordered chain of follow-up questions from a single interview experience. The parenthetical makes the ordering semantic explicit (question ID order = follow-up order), and the fallback sentence names draw_questions as the tool that instead draws scattered questions, so an agent can distinguish them 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?

Gives an explicit when-not rule: if no sufficiently long session exists under the filters, the tool returns "none", and the agent should switch to draw_questions. That is a real routing instruction rather than an implied one. What is missing is guidance on how the four filter dimensions narrow the pool (e.g., whether to loosen filters before giving up) or when to prefer this over question-search tools.

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