Skip to main content
Glama

Index Resume / JD for Search & Match

index_document

Index a resume or job description into RChilli's Search & Match engine.

RChilli's Index endpoint accepts a resume or job description along with the index type, document ID, and indexing options, processes the document content, and stores it against the configured index key in the Search & Match engine.

Once indexed, the document can be searched, matched, updated, and reused across downstream recruitment workflows without re-processing it for every query.

Args: filedata: Original Base64-encoded resume or JD file. Use instead of document_text. filename: Original file name including extension. Required for Base64 input. indextype: Document index type - Resume or JD. documentid: Required unique document ID used for indexing. userkey: RChilli user key. Leave blank to use the authenticated session key. subuserid: Optional sub-user identifier for multi-tenant indexing. index_detail_text: Enable free-text search on the indexed document. commit: Commit the indexing operation. check_duplicate: Check for duplicate documents before indexing. duplicate_fields: Fields used for duplicate checking. Defaults to ['id']. update_duplicate: Update the existing document when a duplicate is found. use_v4: Use the Search & Match v4 endpoint when supported. document_text: Plain-text resume or JD content. Use instead of filedata. The server automatically converts it to Base64.

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": "index_document"
  }
}

Input Schema

NameRequiredDescriptionDefault
commitNo
use_v4No
filedataNo
filenameNo
indextypeNoResume
subuseridNo
documentidNo
document_textNo
check_duplicateNo
duplicate_fieldsNo
update_duplicateNo
index_detail_textNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / document_text
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Document Text"
      +}
    • removedInput schema / properties / userkey
      Removed value: -{
      -  "default": "",
      -  "title": "Userkey",
      -  "type": "string"
      -}
  2. Added

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare non-readOnly, openWorld and non-idempotent, so the description's real contribution is the duplicate-handling story (check_duplicate, duplicate_fields, update_duplicate) and the warning that indexing writes into a remote engine against a configured index key. It also discloses that reusing an indexed document avoids re-processing, which matters for cost-sensitive agents. It stops short of saying what a duplicate hit or a failed commit returns.

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?

The description is front-loaded with a one-line purpose, followed by behavioral context and a clean Args list, so an agent can stop reading early. There is mild redundancy ('processes the document content, and stores it against the configured index key' restates 'index'), and the Args list repeats parameter names the schema already exposes, but nothing is genuinely wasted.

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?

For a 12-parameter, no-output-schema write tool with zero schema coverage, the definition covers every parameter and explains the duplicate and commit semantics an agent needs to call it correctly. The main gap is return behavior: it does not say what the index response contains (index key, duplicate status, document id echo), which matters because there is no output schema to fall back on.

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?

With 0% schema description coverage and 12 parameters, the description carries the full burden and mostly meets it: it documents the filedata/document_text mutual exclusivity, that filename is required for Base64 input, that documentid must be unique, and that userkey defaults to the authenticated session. A few entries are near-tautological ('commit: Commit the indexing operation', 'use_v4: Use the … v4 endpoint when supported'), and none of the parameters have enums, so indextype's allowed values ('Resume or JD') are mentioned but not formally constrained.

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?

The first line names a specific verb and resource — indexing a resume or JD into RChilli's Search & Match engine — and the second paragraph explains what happens to the document (processed and stored against the configured index key). It distinguishes itself implicitly from siblings like extract_resume_data by noting the document can subsequently be searched, matched and reused, but it never names those siblings to make the boundary explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

Usage is implied rather than stated: the description says once indexed the document can be searched and matched, which hints this precedes search_indexed_documents and find_matches_in_index. There is no explicit 'use this when…' statement, no mention of when to prefer extract_resume_data over indexing, and no prerequisites or session/auth guidance beyond the userkey note.

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