Skip to main content
Glama
OpenInbox – Email for AI Agents

OpenInbox – Email for AI Agents

Official

Create inbox

create_inbox

Create a disposable email address that receives mail immediately, returning the address and an inbox_id for follow-up tools. Use it to sign up on sites, get verification codes or links, or test email flows.

Instructions

Create a new disposable email address that can receive email right away. Use it to sign up for a website, receive a verification code or link, or test an email flow. Returns the address and an inbox_id for the other tools.

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_inbox"
  }
}

Input Schema

NameRequiredDescriptionDefault
domainNoOptional custom domain the user has verified in OpenInbox (e.g. "mail.example.com"). Useful when a site blocks shared temporary-email domains. Omit to use OpenInbox's domains.
prefixNoOptional custom local part, e.g. "jane.test" → jane.test@<domain>. Needs a plan with custom aliases.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.2/5.0
Behavior4/5

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

The annotations already declare this is a non-read-only, open-world, non-idempotent, non-destructive creation, so the bar is lower. The description adds real value beyond them: it states the address is usable immediately ('can receive email right away') and names the return values (address and inbox_id) in the absence of an output schema. It could still note that each call spawns a distinct mailbox, but the combined picture is solid.

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 with zero waste: the capability is front-loaded, then usage scenarios, then the return handle. Every sentence earns its place and nothing is padded.

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 simple two-optional-parameter creation tool with annotations present, the definition covers purpose, immediate usability, use cases, and return values, so an agent can call it correctly and knows what it gets back. Only minor operational details (rate limits, whether a fresh mailbox is created on every call) are unstated.

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%, and the schema already documents both optional parameters in depth, including the verified-domain example and the custom-alias plan requirement. The description adds no parameter-level meaning beyond that, so the baseline of 3 is appropriate.

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?

The description opens with a specific verb and resource — 'Create a new disposable email address' — and immediately scopes it ('that can receive email right away'). The verb 'create' alone cleanly separates it from the sibling set (delete_inbox, list_inboxes, read_email), so an agent can route correctly 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 Guidelines4/5

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

It gives concrete use cases — sign up, receive a verification code or link, test an email flow — which is strong when-to-use guidance. The phrase 'for the other tools' signals the inbox_id is the handle needed downstream. It stops short of stating a when-not (e.g., reuse an existing inbox via list_inboxes instead of creating another), so it is clear but not exhaustive.

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