Skip to main content
Glama

面灵AI 面试助手

send_job_apply_instruction

Destructive

把一句话交给用户电脑上的网申 AI,等同于用户在客户端对话框里说了这句话,例如「把投递清单里的岗位都投了」「按我的简历挑 10 个北京的后端校招」。默认交给 Skills 专用的那条常驻对话(没有则新开),传 taskId 则交给指定的对话;对话正在执行时这句不打断,随下一步一并交给 AI 或排队到这一轮结束。网申 AI 据此投递时,每家填到提交前或提交成功时扣 1 家网申可投家数(同一家只扣一次,不限家数期内不扣)。回包为客户端读回的去向(已开始执行 / 已随下一步交给 AI / 排队中)与对话 ID,之后用 get_job_apply_client_status 查看进展与 AI 的回复。需要用户电脑上的「面灵求职网申助手」客户端已登录并打开(关闭窗口后转入后台运行的同样可以);客户端不在线或版本较旧时,工具如实返回原因。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 job_applications: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": {
      "text": "<text>"
    },
    "name": "send_job_apply_instruction"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYes交给网申 AI 的那句话,用用户的口吻写
taskIdNo对话 ID(taskId),从 get_job_apply_client_status 取得

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?

Beyond the annotations (destructiveHint=true, openWorldHint=false), the description discloses the billing model (1 可投家数 charged per company at pre-submit or successful submit, deduplicated per company, waived during unlimited-quota periods), client prerequisites and offline/outdated fallbacks, queueing semantics when a conversation is busy, and the required auth scope. It also mandates informing the user of charges and obtaining consent before execution — exactly the kind of context 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?

It is one dense paragraph, but the core action and the equivalence example come first, followed by routing, queueing, billing, return value, prerequisites and auth in a logical order. Nearly every clause carries operational information; the billing sentence is long but non-redundant.

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?

There is no output schema, yet the description describes the response shape (destination state — 已开始执行 / 已随下一步交给 AI / 排队中 — plus conversation ID), the failure mode when the client is offline or outdated, cost implications, and the required permission scope. Nothing an agent needs to call this safely is missing.

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, but the description adds real meaning: it explains what happens when taskId is omitted (routes to the Skills-dedicated conversation, creating one if absent) versus supplied (targets that conversation), and reinforces that text should be phrased in the user's voice. That behavior-around-parameter context exceeds the schema text.

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 opening sentence states a specific verb and resource — handing one natural-language sentence to the 网申 AI on the user's computer — and anchors it with a concrete equivalence (same as typing it in the client chat box) plus two examples. This clearly separates it from siblings such as add_*_to_apply_list (which build the list) and get_job_apply_client_status (which reports progress).

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 explains the routing choice (default to the Skills persistent conversation, or target a specific one via taskId) and explicitly directs the agent to get_job_apply_client_status afterwards to read progress and the AI's reply. It also states the non-interruption/queueing condition. There is no explicit 'do not use this when…' exclusion, so it falls just short of the top mark.

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