Skip to main content
Glama

MailTester Ninja

Find a professional email address

find_email
Read-onlyIdempotent

Find the work email address of a business contact, for professional outreach, from their first name, last name and company domain. The company's common address formats (first.last, flast, first, firstlast, first_last, f.last) are checked one by one with the company's own mail server, and the first one it accepts is returned. No database is searched and nothing is stored. Stops early when the domain accepts every address (catch-all) and then gives the most common format as "guess". Each format checked counts as one verification. Personal email providers such as gmail.com are refused. Requires a paid MailTester Ninja key.

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": {
      "first_name": "<first_name>",
      "last_name": "<last_name>",
      "domain": "<domain>"
    },
    "name": "find_email"
  }
}

Input Schema

NameRequiredDescriptionDefault
domainYesCompany domain, for example example.com
last_nameYesLast name, for example De La Tour
first_nameYesFirst name, for example Jean-Pierre

Output Schema

NameRequiredDescriptionDefault
codeYes
emailYesThe address the mail server accepted, when found
foundYes
guessYesOn a catch-all domain, the most common pattern; for a full mailbox, that address. Not verified.
triedYesNumber of address patterns checked, each one counted as a verification
formatYesPattern of the returned address: first.last, flast, first, firstlast, first_last or f.last
reasonYes
testedYesEvery address checked, in order, with its verdict
messageYes
confidenceYesFor an address found: high (first and last name in it), medium (an initial, a namesake may share it), low (first name only)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedOutput schema / properties / confidence
      Added value: +{
      +  "anyOf": [
      +    {
      +      "enum": [
      +        "high",
      +        "medium",
      +        "low"
      +      ],
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "For an address found: high (first and last name in it), medium (an initial, a namesake may share it), low (first name only)"
      +}
    • addedOutput schema / properties / format
      Added value: +{
      +  "description": "Pattern of the returned address: first.last, flast, first, firstlast, first_last or f.last",
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / tested
      Added value: +{
      +  "description": "Every address checked, in order, with its verdict",
      +  "items": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "code": {
      +        "type": "string"
      +      },
      +      "email": {
      +        "type": "string"
      +      },
      +      "message": {
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "email",
      +      "code",
      +      "message"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • changedOutput schema / required
      Previous value: -[
      -  "found",
      -  "email",
      -  "guess",
      -  "code",
      -  "message",
      -  "tried",
      -  "reason"
      -]New value: +[
      +  "found",
      +  "email",
      +  "format",
      +  "confidence",
      +  "guess",
      +  "code",
      +  "message",
      +  "tried",
      +  "tested",
      +  "reason"
      +]
  2. Changed6 schema fields changed
    • changedInput schema / properties / first_name / description
      Previous value: -"First name"New value: +"First name, for example Jean-Pierre"
    • changedInput schema / properties / last_name / description
      Previous value: -"Last name"New value: +"Last name, for example De La Tour"
    • removedInput schema / properties / middle_name
      Removed value: -{
      -  "description": "Middle name, if any",
      -  "maxLength": 64,
      -  "type": "string"
      -}
    • addedOutput schema / properties / guess
      Added value: +{
      +  "description": "On a catch-all domain, the most common pattern; for a full mailbox, that address. Not verified.",
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • changedOutput schema / properties / tried / description
      Previous value: -"Number of address patterns checked"New value: +"Number of address patterns checked, each one counted as a verification"
    • changedOutput schema / required
      Previous value: -[
      -  "found",
      -  "email",
      -  "code",
      -  "message",
      -  "tried",
      -  "reason"
      -]New value: +[
      +  "found",
      +  "email",
      +  "guess",
      +  "code",
      +  "message",
      +  "tried",
      +  "reason"
      +]
  3. First observed

TDQS

A4.5/5.0
Behavior5/5

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

The description goes well beyond the readOnly/idempotent annotations: candidate formats are probed one by one against the mail server, the first accepted is returned, no database is searched, nothing is stored, catch-all domains short-circuit to a 'guess', and each checked format costs one verification against a paid key. These are exactly the cost and side-effect details an agent needs before calling.

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?

Purpose and required inputs come first, then behavior, then cost and prerequisites. Every sentence carries distinct information — formats, catch-all handling, per-format credit cost, provider refusal, key requirement — with no filler.

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?

With an output schema present, return values need no explanation, yet the description still clarifies the unusual 'guess' outcome. Combined with cost, auth, and catch-all behavior, an agent has everything needed to decide and invoke correctly.

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 all three parameters are already documented with examples. The description only reinforces that 'domain' means the company domain and that the names are a real contact's; it adds no format or edge-case guidance beyond the schema, so the baseline 3 applies.

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 — find the work email of a business contact — and immediately names the required inputs (first name, last name, company domain). It is clearly distinguishable from the sibling verify_email because it discovers an address rather than validating a known one.

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 frames the intended context ('for professional outreach') and gives an explicit exclusion: personal providers such as gmail.com are refused. It does not explicitly contrast with verify_email, so the agent must infer the find-vs-verify split on its own.

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