Skip to main content
Glama

Prepare interview questions from a resume

prepare_interview_questions
Read-onlyIdempotent

Builds the grounding of a job interview prep for a project, program or product manager, TPM, PMO lead or business analyst from their resume text and, if they have it, the job posting. Use it when someone shares a resume (pasted or attached) before an interview, or asks what a hiring manager will ask them. Returns data read by fixed rules written by practitioners: every resume line word for word with its number; each requirement of the posting with a call (covered, partial, not_found, not_checked) and every resume line found for it; the main requirement; inconsistencies of dates and figures; up to 10 likely questions, each with what the answer must prove and an id (the ids of requirement, resume line, behavioral and industry questions go to check_interview_answer); and a plan by the days left to interview_date (by window when there is no date). checks says what each field means; not_found means the rules found no line, not that the person lacks the experience. Optional: interview_stage and interviewer_title shift the mix of questions; interviewer_profile is read only for subject words; company adds questions from what some large US employers publish, with source links; draft checks the quotes and gap calls of a prep draft against the resume. For practice before an interview, not during it; it does not write answers. English text; contact details are removed first; nothing sent with a call is stored. handoff_code reads the resume and the job posting the person saved on the PM Career Desk site or in its Chrome extension; that code holds them, with personal details removed and encrypted, for up to 2 hours.

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": "prepare_interview_questions"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoThe language the person writes in, as a code such as es, fr or ru; empty or en for English. The result names this language; findings are written in English.
roleNoOptional. One of project-manager, program-manager, technical-program-manager, product-manager, scrum-master, pmo, it-manager, business-analyst, delivery-manager; a title as written (for example Senior Program Manager) is also read. Empty when not sure.
draftNoOptional. A prep draft written from a result of this tool for the same resume and posting, up to 20000 characters. The result is then the check of the draft: its quotes that are not in the resume word for word, its gap calls on requirements where the rules found resume lines, its covered calls where they found none, and its figures not in the resume or the posting. The draft is read in memory only and not stored.
entryNoOptional. Where the person started: directory, site, udemy or other. Counted only; with handoff_code the code's own entry is used.
companyNoOptional. The employer's name as written in the posting.
industryNoOptional. The employer's industry, one of healthcare-life-sciences, financial-services, software-saas, government-public-sector, consulting-services, retail-supply-chain, manufacturing-industrial, energy-utilities; a plain name such as healthcare or banking is also read. Adds questions written for that industry. Empty when not sure.
job_postingNoThe full text of the job posting, as the person gave it. Optional; with it the result adds the requirements, the gaps and questions about them.
resume_textNoThe resume as plain text, copied in full from what the person pasted or from the text of the file they attached. At least the summary and the experience section. May be empty when handoff_code is given.
handoff_codeNoOptional. A handoff code PCD-XXXX-XXXX-XXXX-XXXX that the person made on the PM Career Desk site or in its Chrome extension. The resume and the job posting saved under it are read instead of resume_text and job_posting. A code works for 2 hours, and for 30 minutes after its first read.
interview_dateNoOptional. The interview date as YYYY-MM-DD.
resume_outlineNoOptional structure of the resume: roles with title, company, dates and bullets; summary; skills; certifications; education. Every line must appear word for word in resume_text; lines that do not are left out and counted in the result. Without it the plain text is read.
interview_stageNoOptional. The interview stage: recruiter_screen, hiring_manager, panel, company_round or unknown. Shifts the mix of intro, requirement, resume line and behavioral questions.
job_requirementsNoOptional. The requirement lines of the job posting, each word for word from job_posting; lines that are not are left out and counted in the result. Without them the requirements are read from job_posting.
interviewer_titleNoOptional. The interviewer's job title as the person gave it, up to 120 characters, for example Director of Engineering. Read for the function and level only; no name is needed.
interviewer_profileNoOptional. The text of the interviewer's profile that the person pasted, up to 3000 characters. Contact details are removed and only subject words of a fixed list are kept to choose questions; the text is not returned and not stored.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed11 schema fields changed
    • addedInput schema / properties / draft
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 20000,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": "",
      +  "description": "Optional. A prep draft written from a result of this tool for the same resume and posting, up to 20000 characters. The result is then the check of the draft: its quotes that are not in the resume word for word, its gap calls on requirements where the rules found resume lines, its covered calls where they found none, and its figures not in the resume or the posting. The draft is read in memory only and not stored.",
      +  "title": "Draft"
      +}
    • addedInput schema / properties / entry
      Added value: +{
      +  "anyOf": [
      +    {
      +      "enum": [
      +        "directory",
      +        "site",
      +        "udemy",
      +        "other"
      +      ],
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Optional. Where the person started: directory, site, udemy or other. Counted only; with handoff_code the code's own entry is used.",
      +  "title": "Entry"
      +}
    • addedInput schema / properties / handoff_code
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 64,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": "",
      +  "description": "Optional. A handoff code PCD-XXXX-XXXX-XXXX-XXXX that the person made on the PM Career Desk site or in its Chrome extension. The resume and the job posting saved under it are read instead of resume_text and job_posting. A code works for 2 hours, and for 30 minutes after its first read.",
      +  "title": "Handoff Code"
      +}
    • addedInput schema / properties / interview_stage
      Added value: +{
      +  "anyOf": [
      +    {
      +      "enum": [
      +        "recruiter_screen",
      +        "hiring_manager",
      +        "panel",
      +        "company_round",
      +        "unknown"
      +      ],
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Optional. The interview stage: recruiter_screen, hiring_manager, panel, company_round or unknown. Shifts the mix of intro, requirement, resume line and behavioral questions.",
      +  "title": "Interview Stage"
      +}
    • addedInput schema / properties / interviewer_profile
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 3000,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": "",
      +  "description": "Optional. The text of the interviewer's profile that the person pasted, up to 3000 characters. Contact details are removed and only subject words of a fixed list are kept to choose questions; the text is not returned and not stored.",
      +  "title": "Interviewer Profile"
      +}
    • addedInput schema / properties / interviewer_title
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 120,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": "",
      +  "description": "Optional. The interviewer's job title as the person gave it, up to 120 characters, for example Director of Engineering. Read for the function and level only; no name is needed.",
      +  "title": "Interviewer Title"
      +}
    • addedInput schema / properties / resume_text / anyOf
      Added value: +[
      +  {
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • addedInput schema / properties / resume_text / default
      Added value: +""
    • changedInput schema / properties / resume_text / description
      Previous value: -"The resume as plain text, copied in full from what the person pasted or from the text of the file they attached. At least the summary and the experience section."New value: +"The resume as plain text, copied in full from what the person pasted or from the text of the file they attached. At least the summary and the experience section. May be empty when handoff_code is given."
    • removedInput schema / properties / resume_text / type
      Removed value: -"string"
    • removedInput schema / required
      Removed value: -[
      -  "resume_text"
      -]
  2. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, yet the description adds substantial non-obvious behavior: contact details are stripped, English-only output, nothing sent with a call is stored, handoff_code is encrypted and expires in 2 hours (30 minutes after first read), and 'not_found' means the rules found no line rather than the candidate lacking the experience. That last clarification is exactly the kind of interpretive context an agent cannot get 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.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is one dense paragraph of roughly 250 words in which usage, return shape, privacy guarantees and parameter behavior are interleaved, so the most decisive sentence (when to use it) is buried mid-paragraph. Almost every clause carries real information, but the lack of structure and the run-on sentences cost the reader. Front-loading scope and use-case would fix it without cutting content.

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 15-parameter tool with no output schema, the description does the heavy lifting: it describes each returned field group (resume lines with numbers, requirement calls, main requirement, inconsistency detection, up to 10 questions with ids, day-window plan) and names 'checks' as the self-documenting field. It also covers the handoff_code data source, privacy handling and language limits, so an agent has everything needed to call it correctly.

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 description coverage is 100%, so the baseline is 3; the description earns above that by explaining parameter effects, not just their existence: interview_stage and interviewer_title 'shift the mix' of questions, interviewer_profile is read only for subject words from a fixed list and never returned, company pulls in questions from published large-employer sources, and draft converts the result into a consistency check. Minor loss for not touching several of the 15 params (lang, entry, industry, interview_date) in the prose.

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?

The description names a concrete verb and output: it builds interview prep grounding from resume text plus an optional job posting, for PM/TPM/PMO/BA roles. It also enumerates the returned artefacts (resume lines, requirement calls, questions, day plan). It does not clearly differentiate itself from siblings like prepare_interview_plan or review_resume, which is the only thing keeping it from a 5.

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?

Explicit trigger conditions are given: 'Use it when someone shares a resume (pasted or attached) before an interview, or asks what a hiring manager will ask them.' It also states an exclusion ('For practice before an interview, not during it; it does not write answers') and routes the downstream step to check_interview_answer. It never contrasts with the closest-looking siblings, so it stops short of a 5.

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