screen-resume
Run the full ATS resume screening chain: format compliance → experience relevance → keyword match → gap detection → recommendation. Returns overall verdict (STRONG_MATCH, CONDITIONAL_MATCH, WEAK_MATCH, REJECT, RECONSIDER), pass probability, and prioritized fix list.
Taxonomy
Linnaean classification joined from the algovigilance taxonomy index via the parent config's rank.
| Rank | Value |
|---|---|
| domain | Substrata |
| kingdom | Constructa |
| phylum | Configa |
| class | station-config |
| order | ats |
| family | mcp-tool-config |
Characteristics:
- substrate:
config - domain:
pv - lifecycle:
continuous - authority:
read - compounding:
producer - io:
agent-request→tool-response
Input schema
file_type_compatiblebooleanrequired — Whether the resume file type is ATS-compatible (.docx, .pdf)has_standard_headersbooleanrequired — Whether standard section headers exist (Experience, Education, Skills)uses_simple_formattingbooleanrequired — Whether formatting is ATS-parseable (no tables, columns, text boxes)has_contact_infobooleanrequired — Whether contact info (name, email, phone) is in plain text at topsections_detectedintegerrequired — Number of distinct sections detected in the resumematched_keywordsintegerrequired — Number of job description keywords found in resumetotal_keywordsintegerrequired — Total keywords extracted from job descriptiondirect_experience_yearsinteger — Years of directly relevant experiencetransferable_experience_yearsinteger — Years of transferable experience from adjacent rolesrequired_yearsinteger — Years of experience required by job listingmissing_hard_skillsinteger — Count of required hard skills not found in resumemissing_credentialsinteger — Count of required credentials/certifications not held
Example call
POST /api/mcp
Content-Type: application/json
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "station__ats__screen-resume",
"arguments": {
"file_type_compatible": false,
"has_standard_headers": false,
"uses_simple_formatting": false,
"has_contact_info": false,
"sections_detected": 0,
"matched_keywords": 0,
"total_keywords": 0
}
}
}How to invoke from a client
From any MCP-aware client, add https://algovigilance.com/api/mcp as an MCP server, then call this tool by name. From a raw HTTP client, send the JSON-RPC body above to /api/mcp.
Agent-friendly formats
Working inside an AI assistant? Use the Copy for AI button at the top of this page (or view the raw Markdown) to paste a clean, token-budgeted version of this tool's contract into your conversation.
Related
- All tools (3062 live)
- /api/mcp — endpoint
- /AGENTS.md — agent guide
- /tools/ats__screen-resume/raw.md — this page's Markdown twin