Skip to main content
Glama

add_job

Save a complete job description, company, role, and verified source URL so applications can be reviewed against the original posting.

Instructions

保存用户或宿主浏览器已读取的完整 JD 与真实来源;不能编造邮箱。公开静态官网也可通过 discover_jobs 读取。

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": {
      "company": "<company>",
      "role": "<role>",
      "jd": "<jd>",
      "sourceUrl": "<sourceUrl>"
    },
    "name": "add_job"
  }
}

Input Schema

NameRequiredDescriptionDefault
jdYes
roleYes
companyYes
recipientNo
sourceUrlYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.3/5.0
Behavior3/5

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

Annotations already establish the write, non-destructive, closed-world profile, so the description is not the sole source of behavioral disclosure. It does add meaningful context beyond them: the JD must be complete, the source must be genuine, and the email must never be fabricated — an integrity constraint that materially affects how the agent should populate fields. It says nothing about duplicate handling (e.g., same company+role), validation failures, or what the caller receives on success.

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 and the integrity constraint are front-loaded in the first clause, which is the right ordering for an agent scanning for fit. The second sentence, routing public static sites to discover_jobs, is a brief but justified aside. Nothing is padded or repeated, though the phrasing is terse to the point of being slightly cryptic.

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

Completeness2/5

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

This is a non-destructive write tool with five parameters, zero schema description coverage, and no output schema, so the description is the only place an agent can learn the contract. It covers provenance and the no-fabricated-email rule but leaves duplicate behavior, the role of the optional recipient, why company and role are required, and what a successful call produces entirely unstated. For a data-persistence tool that is a substantial gap.

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 0% across 5 parameters, so the description must carry the burden and only partly does. It adds real semantics for jd ('完整' — complete, not truncated), sourceUrl ('真实来源' — genuine provenance), and indirectly recipient ('不能编造邮箱' — never invent the email). It gives no meaning at all for company and role, leaving two required parameters entirely undefined beyond their names.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a concrete action (保存/store) on a concrete resource (完整 JD 与真实来源 — the full job description plus its genuine source URL), which is more than a restatement of 'add_job'. It also implicitly separates itself from discover_jobs by framing this as persisting already-read data rather than fetching it. It stops short of stating that it creates a job record in the workspace, so an agent must infer the resulting artifact.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

There is partial routing guidance: data must come from what the user or host browser has already read, and public static official sites should be handled by discover_jobs instead. That is a real when-not with a named alternative. However, no guidance covers the other plausible paths (prepare_application, import_resume, etc.), and the conditions for choosing this tool are only implied rather than stated as explicit trigger conditions.

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