Job Application Agent MCP Server

draft_cover_letter

Drafts a cover letter for one vacancy using only CV facts, checks every sentence for grounding, flags issues, and queues the draft for human approval without sending it.

Instructions

Write a cover letter draft for one vacancy, using only facts from the CV.

    Args:
        job_id: The `id` of a vacancy returned by search_jobs. Score it first.

    Every sentence is checked against the CV. `grounded` is false when
    problems are left; they are listed in `issues` for the user. The draft
    is saved and put into the user's approval queue (mark_ready), never
    sent. Each call makes a new draft, so call it once per vacancy.

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_id": "<job_id>"
    },
    "name": "draft_cover_letter"
  }
}

Input Schema

Name	Required	Description	Default
`job_id`	Yes

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 2, 2026

TDQS

A4.5/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and does so: it discloses that every sentence is validated against the CV, that `grounded=false` means unresolved problems surfaced in `issues`, that the draft is persisted into an approval queue via mark_ready, and that nothing is ever sent. It also warns that each call creates a new draft, which is a real non-idempotency hazard.

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?

Purpose is front-loaded in one sentence, then parameters, then behavioral notes — a sensible order. A few lines (the grounding/`issues` restatement) overlap with the output schema and could be tightened, but nothing is padding.

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?

An output schema exists, so return-shape explanation is not required, yet the description still supplies the semantics of `grounded` and `issues` plus the downstream approval flow. The only real gap is nothing about latency/cost of generation for what is presumably an LLM-backed call, which is minor given everything else disclosed.

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 0% — the single parameter is only typed as a string titled 'Job Id'. The description compensates by naming its origin (the id returned by search_jobs) and adding the ordering constraint that the vacancy should be scored first, which is meaning the schema cannot convey.

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 gives a specific verb (write/draft), the exact resource (a cover letter for one vacancy), and a hard constraint (only facts from the CV). It is also distinguishable from every sibling — none of search_jobs, read_cv, score_match or request_approval produces prose.

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 states the prerequisite explicitly ('job_id: the id of a vacancy returned by search_jobs. Score it first') and the cardinality rule ('call it once per vacancy'). It does not spell out when *not* to use it, but the precondition and the once-per-vacancy rule cover the practical decision points.

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

Deploy Server