Skip to main content
Glama

JobYap Job Search

by com.jobyap
OverviewDiscussionsAdmin

Match jobs to a candidate

match_jobs
Read-only

Find and rank the best live postings for one specific candidate, such as someone who shared a resume or described their experience, skills or visa needs. Slow: it reads each posting's full description, so a call can take 10 to 15 seconds. For browsing, listing or counting postings, use search_jobs, which answers in under a second. Filters active jobs by title terms (any of them; a term matches when the title holds all its words), excluded title terms, companies, locations and posting window, then takes the newest 300 of that pool (pool_total says how many matched) and reads each full description. It drops postings with no usable description, postings whose stated minimum years of experience exceed candidate_years by more than 1, and, with needs_sponsorship, postings that refuse sponsorship or require citizenship or a clearance; dropped counts each reason. The rest are ranked by how many skills appear in the description, then newest first. Each result carries skills_matched, years_bar, flags and up to 6 requirement sentences. The screening is heuristic: read finalists in full with get_job.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoResults to return, default 15.
skillsNoSpecific skills and domain terms from the resume, as whole words or phrases. They rank results and never filter.
titlesNoTitle terms, any of which may match. A term matches when the title contains all its words as whole words, in any order: "software engineer" also matches "Engineer, Software". Required unless companies is given.
companiesNoExact company names from list_companies. With titles, a posting must match both.
locationsNocountry-XX (ISO alpha-2) for a country, or state and city identifiers from search_locations. Omit for worldwide.
work_modeNoOnly postings explicitly marked remote or hybrid.
posted_withinNoPosting window: 24h, 7d (default) or 30d.7d
exclude_titlesNoTitle terms that remove a posting, matched like titles, e.g. "senior", "staff", "lead", "manager".
candidate_yearsNoCandidate years of professional experience; drops postings that require more than one year beyond it.
include_anywhereNoWith locations, also keep fully remote "Anywhere" postings. Default true.
exclude_companiesNoCompany names to leave out, case-insensitive, e.g. the current employer.
needs_sponsorshipNoDrop postings that refuse visa sponsorship or require citizenship or a security clearance. Default false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / candidate_years / description
      Previous value: -"Candidate years of professional experience; drops postings that require more than this plus 0.5."New value: +"Candidate years of professional experience; drops postings that require more than one year beyond it."
  2. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare the safe-read profile; the description adds substantial behavior beyond that: the 10-15s latency, the newest-300 pool cap, the three drop heuristics (no usable description, years bar +1, sponsorship/citizenship/clearance), the skills-count ranking, and the explicit caveat that screening is heuristic. This is unusually rich disclosure.

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 purpose, then speed, then the alternative, then mechanics. Dense but nearly every sentence carries actionable information. It is long, though the length is justified by 12 parameters and a non-obvious pipeline.

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 no output schema and 12 parameters, the description still documents the return shape (skills_matched, years_bar, flags, up to 6 requirement sentences), the pool_total and dropped counters, and the full filtering/ranking pipeline. An agent has everything needed to call it correctly and interpret results.

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 baseline is 3, but the description adds real semantics: skills 'rank results and never filter', titles matching semantics, the sponsorship and years drop rules, and the limit-300 interaction. It clarifies how filters compose (titles+companies must both match) beyond the schema.

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?

Starts with a specific verb+resource ('Find and rank the best live postings') scoped to 'one specific candidate', and explicitly contrasts itself with the sibling search_jobs for browsing/listing/counting. An agent can differentiate it from search_jobs and get_job 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 Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit when-to-use (candidate with resume/skills/visa needs), when-not (browsing/listing/counting → use search_jobs, with a latency rationale: 10-15s vs under a second), and a follow-up step (read finalists with get_job). Nothing is left to inference.

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

All JobYap Job Search toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources