Skip to main content
Glama

verify_email

Verify one email address and return its verdict, score, and per-check results, waiting up to about 8 seconds for the job. Its mailbox field says whether the mail server confirmed the mailbox itself: a valid address at Microsoft or Yahoo, which are not asked, or at a catch-all domain, which accepts every address, is unconfirmed. Use it for a single address or a few; for 20 or more addresses use submit_batch, which is built for lists. If the job is still running it returns a job_uuid and a note: then call get_verification with that job_uuid instead of resubmitting. The optional checks list picks which checks run (syntax, mx, smtp, disposable, role, free, catchall). Each check is billed at its own price, returned by get_pricing. Omitting checks runs every check your plan allows, which is the most reliable answer and costs the most tokens; naming fewer costs less. A check outside your plan is refused. Requires the email:verify:single scope.

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": {
      "email": "<email>"
    },
    "name": "verify_email"
  }
}

Input Schema

NameRequiredDescriptionDefault
emailYesEmail address to verify.
checksNoOptional check wire strings (syntax, mx, smtp, disposable, role, free, catchall). Each check is billed at its own price (see get_pricing). Omit to run every check your plan allows, the most reliable answer and the most tokens; naming fewer costs less. A check outside your plan is refused. smtp brings mx, and catchall brings smtp and mx.
idempotency_keyNoOptional idempotency key so repeated calls replay the same job.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • removedInput schema / properties / api_key
      Removed value: -{
      -  "description": "Optional. A pm_live_/pm_test_ key to bill and scope this verification; omit to verify with your own session (billed to your wallet, needs the email:verify:single scope).",
      -  "type": [
      -    "string",
      -    "null"
      -  ]
      -}
    • addedInput schema / properties / checks
      Added value: +{
      +  "description": "Optional check wire strings (syntax, mx, smtp, disposable, role, free, catchall). Each check is billed at its own price (see get_pricing). Omit to run every check your plan allows, the most reliable answer and the most tokens; naming fewer costs less. A check outside your plan is refused. smtp brings mx, and catchall brings smtp and mx.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": [
      +    "array",
      +    "null"
      +  ]
      +}
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations supplied, the description carries the full load and does so: ~8 second wait, async fallback returning job_uuid, per-check billing, plan-based refusal of checks, and the required email:verify:single scope. It also pre-explains the 'mailbox' field's unconfirmed states (Microsoft/Yahoo not asked, catch-all domains), which prevents misreading a good verdict as a bad one.

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?

Front-loaded with the core action and latency, then cost, then the async path — good ordering. It runs long and repeats the checks/billing text already present in the schema, so a sentence could be trimmed without losing meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, so the description must describe returns, and it does: verdict, score, per-check results, the mailbox confirmation field, and the job_uuid-plus-note branch. Combined with the auth scope and billing model, an agent has everything needed to call it and interpret the response.

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 coverage is 100%, so the baseline is 3, and the description largely restates the checks parameter's schema text (check names, omit-to-run-all, cheaper with fewer, out-of-plan refusal) rather than adding syntax or dependency detail. The idempotency_key parameter is never mentioned in the description at all.

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 ('Verify one email address') plus the return payload (verdict, score, per-check results) and explicit single-address scope, which separates it from submit_batch and get_verification. An agent can pick it apart from siblings without opening the schema.

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

Usage Guidelines5/5

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

Gives concrete selection thresholds: 'a single address or a few' here, '20 or more addresses use submit_batch'. It also routes the async case explicitly ('call get_verification with that job_uuid instead of resubmitting'), which is exactly the when/when-not guidance an agent needs.

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