Skip to main content
Glama
Sign In
HireLayer MCP server

HireLayer MCP server

by HireLayer
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Resume Scorer

score_resumes

Evaluates 1 to 50 resumes against a job's criteria, returning each candidate scored from 0 to 1 with a verdict, summary, missing requirements and evidence, best first, to support recruiter decisions.

Instructions

Evaluate 1 to 50 resumes against a job, criterion by criterion, and return them best first: for each, a score between 0 and 1, a verdict (highly_relevant, relevant, marginally_relevant or not_relevant), a summary, the required criteria missing or to verify, and the evidence for each criterion. Give the job as job_text (its criteria are extracted on the way, or pass your own criteria) or as the job_id of a stored job. Give each resume as text or as the application_id of a stored resume; at least one resume of the call holds 30 characters or more. Summaries and explanations are written in the job's language. With precise_ranking, the 10 best are re-ranked against each other, each with a ranking_reason. The result is decision support for a human recruiter, not an automated hiring decision. Costs 1 HireLayer credit per resume evaluated, and 1 more with precise_ranking; a pair already scored costs 0.

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": {
      "resumes": "<resumes>"
    },
    "name": "score_resumes"
  }
}

Input Schema

NameRequiredDescriptionDefault
job_idNoAlone: a job already stored, such as the job_id extract_job_criteria returned. With job_text: store the job under your own id; a new text or new criteria for a job already scored evaluate its stored scores again, 1 credit each.
resumesYesThe resumes to score. Each needs text or application_id.
criteriaNoThe job's own criteria, in the format extract_job_criteria returns; they replace the extraction. Only with job_text.
job_textNoThe job description, at least 30 characters. Give job_text or job_id.
languageNoLanguage of the criteria, summaries and explanations: en, fr, de, es or pt. Only with job_text; defaults to the language of the job's text (English when it is another).
workspaceNoThe client company this call belongs to, when the user recruits for several companies: its HireLayer workspace id (letters, digits and . _ : ~ -, up to 200 characters), e.g. acme-corp. Jobs, resumes and scores stay apart from other clients'. A new id creates a new workspace, so reuse the exact id. Omit it for the user's default workspace.
precise_rankingNoRe-rank the 10 best against each other and explain each place in ranking_reason. 1 credit more for the call.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.1.0

TDQS

A4.6/5.0
Behavior5/5

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

With annotations covering the safety profile, the description still adds genuinely non-derivable behavior: credit cost per resume, extra cost for precise_ranking, zero cost for already-scored pairs, language of generated text following the job, and the guardrail that output is decision support rather than an automated hiring decision. None of this is contradicted by the annotations (a 0-cost cached re-score is consistent with idempotentHint=false, since the call still consumes ranking/credits and writes scores).

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 action and result shape, then inputs, then cost — a sensible order with no filler sentences. It is a single dense block of roughly 150 words, so the cost and disclaimer clauses run together rather than being separated for scanability.

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?

Despite having no output schema, the description fully specifies the returned per-resume fields and the best-first ordering, plus ranking_reason under precise_ranking. For a 7-parameter, credit-metered scoring tool, an agent has everything needed to call it correctly and interpret the response.

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 100%, so the baseline is 3, and the description goes beyond it: it frames job_text/job_id and text/application_id as either/or choices with storage semantics, notes language defaults to the job's language, and explains that precise_ranking re-ranks only the top 10 with a ranking_reason. It does not add color to criteria/weight/threshold semantics, which the schema already carries.

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?

Opens with a specific verb+resource+scale: 'Evaluate 1 to 50 resumes against a job, criterion by criterion, and return them best first.' It immediately enumerates the return shape (score 0-1, verdict enum, summary, missing criteria, evidence), so an agent can distinguish this from parse_resume, extract_job_criteria and search_resumes without opening any schema.

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?

It explicitly tells the agent how to supply the job (job_text vs job_id, with criteria overriding extraction) and each resume (text vs application_id), plus a concrete validity constraint ('at least one resume of the call holds 30 characters or more'). It does not explicitly exclude or route away from siblings (e.g. 'use parse_resume first if you only have a file'), which keeps it 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.

Deploy Server

Other Tools