Skip to main content
Glama

Generate Cover Letter

getmattered_generate_cover_letter
Destructive

Writes a tailored cover letter from a resume and job description, or reads and revises an existing application's letter by application_id. Generates draft text only; nothing is sent.

Instructions

Writes a cover letter for a job, or reads or revises an application's letter by application_id. Sends nothing. Uses AI credits. It reads resume_text first, then the base resume on the account, then the resume-builder document.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "getmattered_generate_cover_letter"
  }
}

Input Schema

NameRequiredDescriptionDefault
resume_textNoThe resume the user pasted or attached in this conversation, as plain text. Left out, the resume already on the user's GetMattered account is used.
company_nameNoName of the company the user is applying to
instructionsNoWith application_id: what to change in that letter, in the user's own words.
application_idNoAn application (an id from getmattered_get_applications). With it, the answer is that application's prepared cover letter.
job_descriptionNoFull text of the target job description. Used with company_name, or replaced by application_id.

Output Schema

NameRequiredDescriptionDefault
urlYes
sourceYesgenerated: newly written; application: the letter already prepared for application_id; refined: that letter, changed as asked.
setupStepNoPresent while account setup is open: the first setup step.
companyNameYes
coverLetterYes
resumeSourceNoWhich resume a new letter was written from.
applicationIdYes
resumeBuildIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv1.13.2
    • changedInput schema / properties / application_id / description
      Previous value: -"Return the cover letter already written for this application (an id from getmattered_get_applications) instead of writing a new one."New value: +"An application (an id from getmattered_get_applications). With it, the answer is that application's prepared cover letter."
    • changedInput schema / properties / company_name / description
      Previous value: -"Name of the company you are applying to"New value: +"Name of the company the user is applying to"
    • changedInput schema / properties / job_description / description
      Previous value: -"Full text of the target job description. Pass with company_name, or pass application_id instead."New value: +"Full text of the target job description. Used with company_name, or replaced by application_id."
    • changedInput schema / properties / resume_text / description
      Previous value: -"The resume the user pasted or attached in this conversation, as plain text. Omit it to use the resume already on the user's GetMattered account."New value: +"The resume the user pasted or attached in this conversation, as plain text. Left out, the resume already on the user's GetMattered account is used."
    • addedOutput schema / properties / setupStep
      Added value: +{
      +  "description": "Present while account setup is open: the first setup step.",
      +  "type": "string"
      +}
  2. Addedv1.9.1

TDQS

A3.8/5.0
Behavior3/5

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

Adds real value beyond the annotations: "Sends nothing" pre-empts the worry that a letter is emailed to the employer, and the resume precedence chain (pasted text, then account base resume, then resume-builder document) explains what the model actually reads. However, annotations flag destructiveHint=true and idempotentHint=false, and the description never says whether revising an existing application_id overwrites the stored letter or whether repeated calls each burn credits.

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 with zero filler, front-loaded with the primary action and followed by the two facts an agent would otherwise get wrong (nothing is sent; credits are spent). Every clause carries information.

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?

With an output schema present, return values need no explanation, and the description covers both invocation modes and the input fallback chain. The one meaningful omission relative to a destructiveHint=true, non-idempotent write is what happens to an existing letter on revise and whether repeated calls are costly.

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 coverage is 100%, so the schema already documents every parameter, establishing the baseline of 3. The description does add genuine meaning on top: the fallback order for resume_text and the fact that application_id replaces company_name plus job_description. That is incremental rather than essential given the already-complete schema.

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?

States a specific verb and resource ("Writes a cover letter for a job") and enumerates the three modes: write, read, revise. An agent can tell the branch points apart without opening the schema, but it is not differentiated from nearby document tools such as refine_application_documents or create_resume_draft, which an agent might plausibly confuse it with.

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 clear mode-selection context: pass application_id to read or revise an existing letter, otherwise supply a job description for a new one. It also warns that the call consumes AI credits, which affects whether to retry. It stops short of explicit exclusions (e.g. when to prefer refine_application_documents over this).

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