OpeningsFirst

Create alert

create_alert

Create an alert (up to 5). New jobs matching it are emailed at the chosen times and shown in new_jobs. Sends one catch-up email of the past two weeks' matches.

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": "create_alert"
  }
}

Input Schema

Name	Required	Description
`name`	No	A short name for the alert.
`email`	No	Email this alert's new jobs (default true).
`roles`	No	Role names or any job titles (up to 3).
`cities`	No	Cities.
`levels`	No	Levels (see list_filter_options).
`keywords`	No	Words preferred in the title.
`searches`	No	Typed searches, any words (up to 3).
`companies`	No	Preferred companies.
`countries`	No	Countries.
`job_types`	No	full_time, part_time, contract, temporary, internship.
`work_modes`	No	remote / hybrid / onsite.
`email_times`	No	twice = 8 am and 6 pm; morning = 8 am.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 1, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations only declare that this is a non-destructive, non-idempotent write. The description adds real behavioral context beyond that: a cap of 5 alerts, that matches are emailed at the chosen times, that they surface in new_jobs, and that one catch-up email covering the past two weeks is sent. It omits what happens when the 5-alert limit is hit and whether any filter is mandatory.

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?

Three short sentences, front-loaded with the verb and the limit, then the user-visible consequences. No filler or repetition of schema detail.

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 creation tool with no output schema, the description covers the important outcome (email delivery, new_jobs visibility, catch-up email) and the cap. It leaves edge cases unaddressed — behavior at the limit and whether at least one filter is required — which keeps it from a 5.

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 100%, so all 12 parameters are already documented in the schema (including the email_times enum). The description only echoes the email_times notion via "chosen times" and adds no semantics for roles, searches, keywords, or the interplay between filters, so baseline 3 applies.

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?

States a specific verb and resource ("Create an alert") and adds a hard constraint ("up to 5"), so an agent knows exactly what operation this performs. It doesn't name update_alert/delete_alert as the alternatives for modifying or removing an existing alert, so sibling differentiation is only implicit.

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?

The description explains the effect of creating an alert (emails at chosen times, appears in new_jobs), which implies the usage context, but never states when to pick this over update_alert, list_alerts, or search_jobs. No prerequisites or exclusions are given.

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

All OpeningsFirst tools Inspect

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

Need Help?