Skip to main content
Glama

JD-to-Resume Matching

score_jd_against_resume
Read-onlyIdempotent

Evaluates how well a candidate's resume matches a job description, with no search index required. Accepts plain text or Base64-encoded files (PDF, DOC, DOCX, RTF, TXT). Returns an overall match score and a detailed explanation based on the job's requirements, skills, qualifications and experience. Processes one resume and one job description per call.

Instructions: Use this tool when a user asks how well a candidate fits a role, wants a match score for a resume and job description, or wants to know why a candidate does or does not fit. Pass the complete resume and the complete job description, either as plain text or as Base64-encoded file content. To match one resume against many jobs, or one job against many candidates, use match_end_to_end or the search and match tools instead.

Args: ctx: MCP context used for authentication. index_key: Optional index or credential context. jd_content: Complete job description as plain text. jd_file_name: Original job description filename. resume_content: Complete resume as plain text. resume_file_name: Original resume filename. jd_base64: Base64-encoded job description. resume_base64: Base64-encoded resume.

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": "score_jd_against_resume"
  }
}

Input Schema

NameRequiredDescriptionDefault
index_keyNoRChilli Search & Match API user key. Leave blank to use the authenticated MCP session userkey.
jd_base64NoOriginal Base64-encoded JD file (PDF, DOC, DOCX, RTF, TXT). Use instead of jd_content. No data URI prefix.
jd_contentNoComplete plain-text Job Description. Use instead of jd_base64. Do not Base64-encode text.
jd_file_nameNoOriginal JD filename including extension. Required when jd_base64 is provided.
resume_base64NoOriginal Base64-encoded resume file (PDF, DOC, DOCX, RTF, TXT). Use instead of resume_content. No data URI prefix.
resume_contentNoComplete plain-text resume/CV. Use instead of resume_base64. Do not Base64-encode text.
resume_file_nameNoOriginal resume filename including extension. Required when resume_base64 is provided.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds real value beyond them: no search index required, accepted file formats (PDF, DOC, DOCX, RTF, TXT), one resume and one JD per call, and the general shape of the return. It stops short of saying whether the score is normalized (e.g., 0-100) or how long processing takes.

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?

The opening paragraph and Instructions section are well front-loaded and earn their place. The trailing Args block largely restates the schema, including an unused ctx entry, which is filler in a description. Structure is clear but not lean.

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 no output schema, the description correctly steps in to describe the return (overall match score plus explanation covering requirements, skills, qualifications, experience). Acceptable inputs and the single-pair constraint are covered. It omits that all seven parameters are technically optional and that at least one content or base64 pair must be supplied, a meaningful edge for invocation.

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 each parameter's meaning, including the plain-text vs Base64 alternative and the filename requirement, is already documented. The description reinforces that the full document must be passed rather than excerpts, but adds no format, size, or precedence rules beyond the schema. A baseline 3 is appropriate.

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 resources: evaluates how well a resume matches a job description, returning an overall score plus explanation. It also flags the no-search-index requirement, which shapes expectations. It does not, however, differentiate itself from the near-identical sibling score_resume_against_jd, leaving ambiguity between two same-shaped tools.

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 concrete triggers (user asks how well a candidate fits, wants a match score, or wants a rationale) and routes batch scenarios to match_end_to_end or the search/match tools instead. The one gap is that it never explains when to choose this over score_resume_against_jd, which appears to do the same thing.

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