Skip to main content
Glama

Set Resume

getmattered_set_resume
Destructive

Sets the base resume that every job application is tailored from, using resume text, an https file link, a saved document, or an attached file. Replaces the current base resume.

Instructions

Sets the base resume every application is tailored from, from exactly one source. A new upload uses AI tokens; a saved document does not. A local file path is not a URL. The resume is saved unchanged. It replaces the user's current base resume; the old one stays in their documents.

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_set_resume"
  }
}

Input Schema

NameRequiredDescriptionDefault
resume_urlNoAn https link to the resume file: PDF, DOCX or plain text, up to 10 MB. Either this, resume_text or document_id.
document_idNoOne of the user's saved resumes to make the base (an id from getmattered_get_account). Free. Either this, resume_text or resume_url.
resume_fileNoA resume file the user attached in ChatGPT, as the file itself. GetMattered reads it once: PDF, DOCX or plain text, up to 10 MB.
resume_textNoThe user's resume text exactly as they gave it, word for word, with every date, employer, title and fact unchanged. Either this, resume_url or document_id.

Output Schema

NameRequiredDescriptionDefault
parsedYesFalse when the resume is still being read. getmattered_get_account shows when it is done.
sourceYes
fullNameYes
documentIdYesThe resume now used as the base for every application.
skillsCountYes
currentJobTitleYes
preferencesSeededYesTrue when empty job preferences were filled from this resume.
suggestedJobTitlesYes
onboardingCompletedYesTrue when the account setup is finished, so GetMattered searches for this user.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv1.13.2
    • changedInput schema / properties / document_id / description
      Previous value: -"One of the user's saved resumes to make the base (an id from getmattered_get_account). Free. Pass this OR resume_text OR resume_url."New value: +"One of the user's saved resumes to make the base (an id from getmattered_get_account). Free. Either this, resume_text or resume_url."
    • changedInput schema / properties / resume_file / description
      Previous value: -"In ChatGPT the user can attach a resume file; pass it as resume_file. It is downloaded once, right away: PDF, DOCX or plain text, up to 10 MB."New value: +"A resume file the user attached in ChatGPT, as the file itself. GetMattered reads it once: PDF, DOCX or plain text, up to 10 MB."
    • changedInput schema / properties / resume_text / description
      Previous value: -"The full text of the resume. Pass this OR resume_url OR document_id."New value: +"The user's resume text exactly as they gave it, word for word, with every date, employer, title and fact unchanged. Either this, resume_url or document_id."
    • changedInput schema / properties / resume_url / description
      Previous value: -"An https link to the resume file: PDF, DOCX or plain text, up to 10 MB. Pass this OR resume_text OR document_id."New value: +"An https link to the resume file: PDF, DOCX or plain text, up to 10 MB. Either this, resume_text or document_id."
    • changedOutput schema / properties / parsed / description
      Previous value: -"False when the resume is still being read; call getmattered_get_account in a minute."New value: +"False when the resume is still being read. getmattered_get_account shows when it is done."
  2. Addedv1.9.1

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and openWorldHint=true, but the description adds crucial nuance the annotations cannot: the old base resume is not deleted, it 'stays in their documents', and the resume is saved unchanged. It also discloses the token cost of uploads, which is invisible from structured fields.

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?

Four short sentences, all front-loaded with the core action and source constraint first. Slightly telegraphic fragments ('A local file path is not a URL') but nothing is wasted.

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 a destructive mutation tool with zero required parameters, the description supplies the key facts an agent needs: exactly one source, cost tradeoff, and that the prior resume persists. An output schema exists, so return values need no explanation; only stricter guidance on picking among document_id/resume_url/resume_file is missing.

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% with rich per-parameter descriptions, so the schema already does most of the work. The description adds only marginal semantics beyond it: that exactly one source must be chosen and that resume_text is stored verbatim ('saved unchanged'), plus the local-path-is-not-a-URL clarification.

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 ('Sets the base resume every application is tailored from') plus the key scope constraint 'from exactly one source'. It is clearly distinct from siblings like create_resume_draft or optimize_resume, though it never names an alternative explicitly.

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 genuine decision rule: a new upload costs AI tokens while a saved document is free, which steers the agent toward document_id when available. Also warns 'A local file path is not a URL'. No explicit when-not-to-use condition is stated.

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