Skip to main content
Glama
jobinja-employer-mcp

jobinja-employer-mcp

by saeedsepehr

Screen applicants (compact digest)

screen_applicants
Read-only

Generate a compact applicant screening digest per page, with profile fields and resume excerpts, to help you shortlist promising candidates using fewer tokens.

Instructions

Compact screening digest of one page (up to 25) of applicants, for fast, low-token shortlisting.

For each applicant: headline, status, star, notes, folders, key profile fields (work history, education, skills) and the first resume_chars characters of the PDF resume text. Gender, birth year, marital status and contact details are left out on purpose. Read the digests, then use get_resume_text / get_applicant only for the promising ones. Takes about a minute per page; opening pending applicants marks them as seen.

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": {
      "post": "<post>"
    },
    "name": "screen_applicants"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNo
postYes
statusNo
resume_charsNo
profile_charsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.1

TDQS

A3.8/5.0
Behavior2/5

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

The description is unusually informative about behavior: it discloses field inclusion/exclusion, token-cost tradeoffs, per-page latency, and the side effect that 'opening pending applicants marks them as seen'. However, that side effect conflicts with the declared readOnlyHint=true annotation, so an agent relying on the annotation's safety guarantee would be misled. Content is rich but the safety-relevant inconsistency with structured metadata caps the score.

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 purpose and scope, then the returned fields, then the routing advice. Dense but each sentence carries information; only the bilingual coda about usage is redundant with the earlier routing sentence.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, and the description does a good job describing the digest contents and omissions, so the return shape is covered. But with 0% schema coverage and 5 parameters, key inputs (required `post`, `status`, `profile_chars`) remain unexplained, leaving an agent guessing how to scope the screening call.

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 0%, so the description must carry the burden, and it only partially does: it explains resume_chars ('first `resume_chars` characters of the PDF resume text') and page size ('up to 25'), and gestures at profile_chars via 'key profile fields', but says nothing about the required `post` parameter or the `status` filter. The two most decision-relevant parameters are left undefined.

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?

States a specific verb and resource ('Compact screening digest of one page (up to 25) of applicants') plus the exact field set returned, so an agent can distinguish it from get_applicant and get_resume_text immediately. The stated intent, fast low-token shortlisting, frames the resource precisely.

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?

Explicitly says to read digests first and to call get_resume_text / get_applicant only for promising applicants, naming the alternatives and the condition that selects them. It also gives a cost expectation ('about a minute per page') that supports the bulk-vs-single decision.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.