Skip to main content
Glama

Resume Data Extraction

extract_resume_data
Read-onlyIdempotent

Extracts structured data from a resume or CV supplied as plain text or a Base64-encoded document. Returns candidate information such as contact details, skills, work experience, education, certifications, and taxonomy-enriched data for AI recruiting workflows. Supports multiple languages with English-normalized output.

Use this tool when a user asks to extract resume data, read candidate details, identify skills and employment history, or convert resume content into structured information for recruiting workflows.

Provide either resume_text containing the complete, verbatim resume text, or resume_base64 containing a Base64-encoded document, but not both. When using resume_base64, include the original filename and extension. For a resume available at a public URL, use extract_resume_data_from_url instead.

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": "extract_resume_data"
  }
}

Input Schema

NameRequiredDescriptionDefault
filenameNoOptional for resume_text (default 'inline_resume.txt'). Required for resume_base64 and must include the original file extension.
resume_textNoComplete, verbatim plain-text of the resume/CV — every line exactly as in the original. Do NOT summarise, paraphrase, or base64-encode; pass raw text.
resume_base64NoRaw Base64-encoded resume file content (PDF, DOC, DOCX, RTF, TXT). Provide the original filename. Use either resume_text or resume_base64, not both. Do not include a data URI prefix.

Output Schema

NameRequiredDescriptionDefault
dataYesTool-specific result payload. The exact fields depend on which tool produced this result.
metaYesRequest metadata: unique trace ID and server-side processing latency.
successNoAlways ``true`` for a successful result. Check this field first to distinguish success from error envelopes.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / filename / description
      Previous value: -"Optional original file name (default 'inline_resume.txt'). A '.txt' extension is appended automatically if missing."New value: +"Optional for resume_text (default 'inline_resume.txt'). Required for resume_base64 and must include the original file extension."
    • addedInput schema / properties / resume_base64
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Raw Base64-encoded resume file content (PDF, DOC, DOCX, RTF, TXT). Provide the original filename. Use either resume_text or resume_base64, not both. Do not include a data URI prefix.",
      +  "title": "Resume Base64"
      +}
  2. Added

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, and openWorld, so the safety profile is covered; the description adds behavior beyond that by disclosing multilingual input with English-normalized output and taxonomy enrichment of the results. It does not discuss size limits, rate limits, or what happens when parsing fails, which leaves some operational gaps for a document-ingestion tool.

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?

Structure is front-loaded correctly: capability first, then return contents, then usage triggers, then input constraints. It loses a point for mild redundancy, since the usage paragraph largely re-enumerates the capabilities already listed in the first sentence (skills, employment history, structured information).

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?

With rich annotations, an output schema, and full parameter documentation, the description covers the remaining burden: what the tool consumes, what it returns conceptually, bilingual handling, and the URL sibling alternative. Nothing an agent needs in order to select and call this correctly 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 description coverage is 100% and each parameter already documents its role, including the filename-extension rule and the do-not-paraphrase instruction for resume_text. The description restates the either/or exclusivity and the filename requirement, adding reinforcement but no new semantics beyond the schema. Baseline 3 applies when the schema does the heavy lifting.

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?

The opening sentence gives a specific verb (Extracts) plus resource (structured data from a resume or CV) and names the accepted input forms (plain text or Base64 document). It then enumerates the returned categories (contact details, skills, work experience, education, certifications, taxonomy-enriched data), so the agent knows exactly what this produces without opening the output schema.

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?

It states explicit trigger conditions ('when a user asks to extract resume data, read candidate details, identify skills and employment history') and names the alternative for a distinct case: use extract_resume_data_from_url for a resume at a public URL. It also flags the input exclusivity rule ('provide either... but not both'), which prevents a common misuse.

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