Skip to main content
Glama
DINQ-labs

openpeoplerouter

Official
by DINQ-labs

people_contact_find

Find a person's work email or phone number, or verify an address you already have. Specify what you need and optionally pin a provider.

Instructions

How to reach one person: their work email, their phone when you ask for it, and whether an address you already hold is real. Use vendor to pin a provider. Returns outcome, normalized output, raw provider data and _meta.tried. Provider API charges are billed directly to your provider account.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
wantNoemail | phone | verify | both. A phone costs several times an email, so it is only looked for when asked for. Passing an email you already hold and want='verify' checks it rather than finding one. (default email)
emailNoA work email address
domainNoThe employer's domain, no www and no @
vendorNoPin one vendor or endpoint id instead of routing
companyNoThe employer's name
full_nameNoThe person's full name
last_nameNoFamily name; pair it with first_name
waterfallNoFalse stops at the first vendor instead of trying the next
first_nameNoGiven name; pair it with last_name
linkedin_urlNohttps://www.linkedin.com/in/<slug>
company_websiteNoThe employer's website, when you have a URL rather than a bare domain
linkedin_handleNoThe <slug> from a LinkedIn URL, without the /in/

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

No annotations are provided, so the description carries the behavioral burden. It discloses the return shape (outcome, normalized output, raw provider data, _meta.tried), the fact that provider charges are billed directly, and the conditional behavior around phone lookups. It could mention failure handling or required identifiers, but for a read-style contact lookup this is solid transparency.

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?

The description is four tight sentences with no filler. It front-loads the core purpose, then covers provider selection, return data, and billing. Every sentence adds useful information.

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?

The description covers purpose, output, and billing, and an output schema exists, so return values are documented elsewhere. However, with 12 optional parameters and no annotations, it does not state what minimum identifiers are needed or how to choose among full_name, domain, email, etc. That leaves some invocation ambiguity for the agent.

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%, so the schema already explains all 12 parameters in detail. The description reinforces vendor, phone, and verify semantics, but it adds little beyond what the schema provides. Baseline 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 'How to reach one person', which states the tool's specific job: finding contact details for a single individual. It further specifies email, phone, and verification of an existing address, and the phrase 'one person' distinguishes it from sibling tools like people_search or people_enrich.

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 clear context: this is for reaching one person, and it notes that phone is only fetched when requested. It also advises using vendor to pin a provider. However, it does not explicitly name alternative tools or state when not to use this tool, though the 'one person' framing implies the distinction.

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