Skip to main content
Glama
Sign In

Emploist

by com.emploist
OverviewDiscussionsAdmin

Create a job

create_job

Creates a job as a draft, or publishes it (open) right away. Drafts only need a title; publishing also needs a description and a finished application form. Without a form, it gets the preset fields (full name, email, resume). Without stages, it gets the default ones. Publishing puts it on the careers page, so confirm with your user first.

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": {
      "title": "<title>",
      "status": "<status>"
    },
    "name": "create_job"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleYes
stagesNoStage names in order; the first is the inbox, where new applications land. Their emails to applicants start switched off.
statusYes"draft", or "open" to publish it.
locationNoWhere the job is, e.g. Berlin. A saved one with the same name (in any letter case) is used, or a new one is saved. Null for none.
workModeNoNull for not set.
departmentNoA department's name, e.g. Engineering. A saved one with the same name (in any letter case) is used, or a new one is saved. Null for none.
descriptionNoHTML with only these tags: p, br, h2, h3, strong, em, u, a (http, https, or mailto links), ul, ol, li.
employmentTypeNoNull for not set.
applicationFormNoThe whole application form, in order. It must have exactly one each of the preset elements { type: "full-name" }, { type: "email" }, and { type: "resume" }, which have no other fields. Other elements: questions { type: "phone" | "short-answer" | "long-answer" | "yes-no", label, helpText, required }; choices { type: "single-choice" | "multiple-choice" | "dropdown", label, helpText, required, options: [{ label }] }; { type: "linear-scale", label, helpText, required, max (2–10), minLabel, maxLabel }; { type: "checkbox", text (HTML; only links), required }; { type: "heading", text }; { type: "text", text }. helpText, minLabel, and maxLabel may be empty strings. Leave out ids for new elements and options; keep the ids of existing ones (from get_job) so earlier applications' answers stay matched to them.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.4/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing defaulting behavior (preset full-name/email/resume fields, default stages) and the real-world side effect that publishing exposes the job on the careers page. The annotations already cover safety (non-destructive, non-idempotent), so this added context is the valuable part. It does not say whether repeated calls create duplicates, which matters given idempotentHint=false.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, front-loaded with the mode split, then defaults, then the confirmation warning. No filler and nothing repeated from the schema's field descriptions.

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?

Covers the creation semantics, defaults, and the publish warning for a 9-parameter mutation tool with no output schema. The main gap is that it never says what comes back (e.g., the new job's id) for follow-up calls like add_stage or update_job_details, which an agent chaining operations would want.

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 high (89%), so the baseline is 3, but the description adds cross-parameter meaning the schema cannot express: which parameters become effectively required when status is "open" versus "draft", and what happens when applicationForm or stages are omitted. That conditional dependency is the key semantic the schema lacks.

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 ("Creates a job") and immediately distinguishes the two modes it supports: draft vs. published/open. That separates it cleanly from siblings like change_job_status, update_job_details, and duplicate_job without needing their schemas.

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?

Gives concrete conditions for each mode: a draft needs only a title, while publishing also needs a description and a finished application form. It also adds a usage caution ("confirm with your user first") for the public-facing path. It does not name sibling alternatives such as change_job_status for converting a draft later, 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.

All Emploist 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