Skip to main content
Glama

Tailor a resume to a job post

create_tailored_resume

Use this when the user provides a resume or CV (attached PDF or pasted text) and a specific job posting, and wants a tailored resume as a finished PDF. One call does everything: reads the resume, analyzes the job post, rewords the experience with the posting's vocabulary without inventing skills, fits it on one page and returns the PDF with a preview card. Works for any job, internship or apprenticeship (alternance), in French or English. Pass the job post text; resolve a job URL to its text first. The resume is written in the job post's language. Optional: guestToken returned by an earlier Matchaa call, templateId when the user asked for a design, language only when the user wants another resume language. Do not use for cover letters, interview preparation or general career advice. For changes to a delivered resume, use update_resume or rewrite_resume_section with the returned operationId and guestToken.

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": {
      "offerText": "<offerText>"
    },
    "name": "create_tailored_resume"
  }
}

Input Schema

NameRequiredDescriptionDefault
cvFileNo
cvTextNo
languageNo
offerTextYes
guestTokenNo
templateIdNo

Output Schema

NameRequiredDescriptionDefault
errorNo
scoreNo
statusYes
changesNo
languageNo
recoveryNo
templateNo
proposalsNo
guestTokenNo
targetRoleNo
downloadUrlNo
operationIdYes
documentStageNo
expiresInSecondsNo
onePageOmissionsNo
retryAfterSecondsNo
missingRequirementsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations only declare readOnly=false, destructive=false, openWorld=false; the description goes well beyond them by describing the full pipeline, the no-invention constraint on skills, the one-page constraint, the dual-language behavior, and that the response includes a PDF plus a preview card and an operationId. It does not mention cost, latency, rate limits, or whether prior resumes are overwritten, which keeps it off a 5.

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 trigger condition, then capability, then constraints, then alternatives — a sensible order with no filler sentences. It is dense and long for a description, but each clause carries distinct operational information rather than restating the name or the schema.

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?

For a six-parameter, nested-input tool with an output schema, this covers trigger, prerequisites, per-parameter intent, language behavior, output shape, and follow-up routing. Return-value detail is legitimately left to the output schema, so nothing an agent needs to invoke it correctly is missing.

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%, so the description carries the full burden and mostly does: it explains that the CV arrives as an attached PDF or pasted text (cvFile vs cvText), that offerText is the job post text with URLs resolved beforehand, that guestToken comes from an earlier Matchaa call, that templateId applies only when a design was requested, and that language is for exceptions only. Only cvFile's nested fields (file_id, download_url, file_name) and validation limits are left to the 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 artifact ("tailored resume as a finished PDF") and enumerates the internal steps: reading the CV, analyzing the post, rewording without inventing skills, fitting to one page. It cleanly separates itself from cover letters and from update_resume/rewrite_resume_section, but never addresses the near-identically named sibling tailor_resume, so an agent choosing between the two gets no disambiguation from this text.

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?

Gives an explicit trigger condition (user supplies a resume or CV plus a specific job posting and wants a finished PDF), a prerequisite step ("resolve a job URL to its text first"), and explicit exclusions (cover letters, interview preparation, general career advice). It also routes follow-up edits to update_resume or rewrite_resume_section with the returned operationId and guestToken.

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.

Resources