Skip to main content
Glama

Icypeas (Unofficial)

Icypeas Find Email

icypeas_find_email
Read-onlyIdempotent

Find a work email by first name, last name and company domain/name, via Icypeas. Icypeas runs searches asynchronously server-side; this call waits for the result rather than handing back a bare task id. Example: icypeas_find_email({ first_name: "Patrick", last_name: "Collison", domain_or_company: "stripe.com", _apiKey: "your-icypeas-key" })

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "_apiKey": "your-icypeas-api-key",
      "last_name": "Collison",
      "first_name": "Patrick",
      "domain_or_company": "stripe.com"
    },
    "name": "icypeas_find_email"
  }
}

Input Schema

NameRequiredDescriptionDefault
_apiKeyNoYour Icypeas API key (get one from the API section of your icypeas.com dashboard).
last_nameNoPerson's last name, can be empty if first_name is given.
first_nameNoPerson's first name, can be empty if last_name is given.
domain_or_companyYesCompany domain or company name, e.g. "stripe.com" or "Stripe".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / first_name / description
      Previous value: -"Person's first name — can be empty if last_name is given."New value: +"Person's first name, can be empty if last_name is given."
    • changedInput schema / properties / last_name / description
      Previous value: -"Person's last name — can be empty if first_name is given."New value: +"Person's last name, can be empty if first_name is given."
  2. First observed

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive, open-world. The description earns credit for one genuinely useful disclosure beyond them: Icypeas searches asynchronously server-side but this call blocks for the result, so the agent needn't poll. It says nothing about latency, timeouts, credit consumption, or failure/not-found behavior.

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?

Purpose and the async/blocking caveat are both front-loaded in two tight sentences, and the worked example disambiguates the parameter set. The inline example is slightly bulky but serves a real disambiguation purpose; nothing is wasted.

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

Completeness3/5

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

With four fully documented parameters and strong annotations, most of the burden is already met. However there is no output schema, and the description never says what a result contains (found email, not-found signal, status/confidence), which matters for a lookup whose miss case drives agent behavior.

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 states that first_name and last_name may each be empty if the other is given, plus domain_or_company examples. The description only restates that the lookup uses first name, last name and domain/company, adding no constraint or format detail beyond the schema, 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?

A specific verb plus resource ("Find a work email") with the exact input triple named, so the agent knows precisely what the tool produces from what inputs. It doesn't distinguish against siblings, but no sibling in the list competes with email lookup, so the omission is minor.

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?

Usage is implied by the input triple (it's the tool for turning a name + company into a work email), and the example shows a concrete call. There is no explicit when-to-use/when-not guidance, no statement about what to do when domain is unknown, and no note on what happens when no email is found.

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.