Skip to main content
Glama
DrawOffer MCP Server

DrawOffer MCP Server

by ql-link

新增岗位

create_job

Save a job description to DrawOffer and automatically create a pending application record; return the existing record if the job is already saved.

Instructions

把一个岗位 JD 保存到 DrawOffer,并自动生成一条「待投递」记录。同一岗位已存在时返回已有记录。需要读写权限的 Key。

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": {
      "job_title": "<job_title>",
      "company_name": "<company_name>"
    },
    "name": "create_job"
  }
}

Input Schema

NameRequiredDescriptionDefault
notesNo个人备注
skillsNo技能关键词
job_titleYes岗位名称
work_cityNo工作城市
source_urlNo岗位原始链接
descriptionNoJD 正文:职责与要求
salary_textNo薪资原文,例如「25-35K·15薪」
company_nameYes公司名称

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

A4.2/5.0
Behavior4/5

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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true), and the description adds real value on top: the write requires a read-write Key, the call has a hidden side effect of creating a 待投递 record, and duplicate jobs return the existing record. The dedup statement is consistent with idempotentHint=false because a new 待投递 record may still be produced, though the description could say so explicitly.

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?

Three short sentences, front-loaded with the action and side effect, then the duplicate rule, then the auth prerequisite. Every sentence carries distinct information with no repetition of the schema.

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 an 8-parameter write tool with no output schema, it covers purpose, side effect, dedup behavior, and auth needs, so an agent can call it correctly. It could add one clause on what the response contains (new vs existing record, any identifier) and on validation failures such as a malformed source_url.

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% with per-field Chinese descriptions (job_title, company_name, description, source_url, etc.), so the schema carries parameter meaning. The description adds nothing about field usage, which of the 8 fields are optional in practice, or how skills/notes affect storage — acceptable baseline given full coverage.

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+resource (save a job JD to DrawOffer) and immediately names the non-obvious side effect (auto-generating a 「待投递」 record), which tells an agent exactly what this does versus list_jobs/get_job. It also disambiguates the write path from the sibling create_application by explaining that the application record here is created implicitly.

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 a concrete prerequisite ('需要读写权限的 Key') and a call-again condition ('同一岗位已存在时返回已有记录'), so the agent knows it can be retried safely on duplicates. It stops short of explicitly contrasting with create_application for the case where the agent wants an application without a job record, so no true exclusions are stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.