Skip to main content
Glama

Write a cover letter for a job

generate_cover_letter

Write the cover letter for a vacancy in the user's tracker, from their resume and the analysis, with an optional tone, length, up to three of the vacancy's key_strengths to lead with, and a personal note. The letter is written in the user's profile language and states only facts from the resume; a resume with no work history still gets a letter, built from its summary and skills. The letter is saved on the vacancy's Cover Letter tab in the web app, the same letter the web and the browser extension write. When the vacancy already has a letter, this replaces it: the new one is written with the previous version in view and the change in options, and an option not given keeps the value the previous letter used. Runs asynchronously — returns a task_id; get_task_status reports when it is written, and get_vacancy_detail then shows has_cover_letter: true. The letter text itself is not returned. Spends one cover letter from the plan (the free plan has one a month); replacing an existing letter spends another one. Returns 'not_found' if the vacancy does not belong to the current user, 'no_resume' if the user has no resume, 'limit_exceeded' naming the day it frees up if the plan allowance is used up.

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": {
      "input": "<input>"
    },
    "name": "generate_cover_letter"
  }
}

Input Schema

NameRequiredDescriptionDefault
inputYes

Output Schema

NameRequiredDescriptionDefault
statusNoprocessing
task_idYesBackground task id; get_task_status reports when the letter is written.
vacancy_idYesId of the vacancy analysis the letter is for.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations only say it is a non-idempotent, non-destructive write; the description goes far beyond that with async task_id semantics, the plan-credit cost (including that a replacement costs another credit), the limit_exceeded message naming the free-up day, and the three named error codes. It also discloses two non-obvious behaviors: a resume with no work history still produces a letter, and an omitted option inherits the previous letter's value rather than a default.

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?

Front-loaded with the action, then the inheritance rule, async lifecycle, cost, and error codes — every sentence carries operational weight. It is a single dense paragraph, so the async/cost/error mechanics would scan faster as separated clauses, but nothing is filler.

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?

Covers every decision an agent must make for a costly, asynchronous, overwriting generation tool: required input, option inheritance, credit spend, where the result lands, how to poll, and the failure envelope. With an output schema present, it correctly declines to describe return payloads beyond the task_id and error tokens.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although the top-level schema coverage reads 0%, the description independently explains the role of each option: optional tone and length, up to three key_strengths to lead with, and a personal note that is the only user-authored content admitted into the letter. It adds meaning the enum lists cannot, such as the letter being written in the profile language and unbacked strengths being dropped.

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 — 'Write the cover letter for a vacancy in the user's tracker' — plus the inputs it derives from (resume and analysis). No sibling tool writes cover letters, so the boundary is unambiguous even without naming an alternative.

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

Usage Guidelines5/5

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

Explicitly handles the when: it names prerequisites ('no_resume'), the replacement case ('When the vacancy already has a letter, this replaces it'), and the exact follow-up path (get_task_status, then get_vacancy_detail showing has_cover_letter: true). It also tells the agent the letter text is not returned, which prevents a wrong retrieval attempt.

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.