Argorant

Find a person's work email

argorant_find_email

Destructive

Find one person's work email from their first name, last name and company domain, checked live. Use it when the user names a specific person at a specific company. For more than 5 people use argorant_find_emails, to search people by job, industry or place use argorant_preview_people and argorant_reveal_people, and to check addresses the user already has use argorant_quote_verification. Each person costs 1 credit when an email is found and confirmed, and 1 credit when the company's domain accepts every address (catch-all). In that case the most likely address is returned and marked unconfirmed. It costs 0.25 credits when nothing is found. Nothing is charged for invalid input, for a domain that does not exist or cannot receive email, or when the check cannot be finished right now (status retry_later). Credits are the account's shared credits. Every call is charged by its result, so ask the user before you spend credits and tell them the price. Never repeat a lookup that returned not_found, and never loop over many people with this tool. Each account can do about 30 lookups a minute and 2,000 a day. These are safety limits and cost nothing, and an account whose lookups almost never find anything is slowed down (rate_limited with retry_after_seconds), never charged more. status valid means found and confirmed, so it is safe to use. catch_all is the best guess at a domain that accepts every address, unconfirmed and it may bounce. The others are not_found, no_mail_domain and retry_later. Tell the user which addresses are unconfirmed. Returns email, status, confirmed, confidence (0 to 100), credits_charged, the credits left and a plain message to pass on to the user. More in the docs at https://docs.argorant.com/docs/agents/tools#find-work-emails

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": "argorant_find_email"
  }
}

Input Schema

Name	Required	Description
`domain`	Yes	The company's domain or website, such as linfieldhq.com, not a free mail domain such as gmail.com.
`last_name`	Yes	Person's last name
`first_name`	Yes	Person's first name

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 8, 2026

TDQS

A4.2/5.0

Behavior3/5

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

Annotations already flag this as a costly, non-read-only, open-world call (readOnlyHint=false, destructiveHint=true), so the credit pricing and rate-limit disclosure adds real context rather than defining safety from scratch. The status vocabulary (valid, catch_all, not_found, no_mail_domain, retry_later) and the catch-all bounce risk are genuinely useful behavior beyond the annotations. It does not spell out authentication requirements or exactly what argument shapes trigger the zero-charge invalid-input path.

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 purpose and routing before cost details, and every block is topic-coherent. It runs long and some status/return detail overlaps with what the output schema already carries, so it could lose a sentence or two without harm.

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?

For a three-parameter, paid, open-world lookup with an output schema, an agent gets routing rules, cost per outcome, rate limits, retry semantics, and status interpretation. With the output schema covering the return shape, nothing decision-critical is missing.

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% and each of the three parameters is documented in the schema, including the free-mail-domain restriction on domain, so the schema carries the load. The description restates the inputs but adds no format, normalization, or edge-case detail (e.g. hyphenated names, subdomains) beyond what the schema says. 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 concrete verb and resource ("Find one person's work email") with the exact inputs (first name, last name, company domain) and a distinguishing trait ("checked live"). It explicitly separates itself from argorant_find_emails, argorant_preview_people, argorant_reveal_people, and argorant_quote_verification, so no schema inspection is needed to pick it.

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 a positive trigger ("the user names a specific person at a specific company") and four explicit alternatives with the condition that selects each (more than 5 people, search by job/industry/place, verifying addresses already held). It also adds prohibitions: never repeat a not_found lookup, never loop over many people with this tool, and confirm spend with the user first.

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

All Argorant 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.