Skip to main content
Glama

Lovie Company Formation

Enrich Person

connection_enrich_person
Read-only

Finds contact details for one person (email, phone, LinkedIn URL, title, company, photo) across the contact-enrichment providers the company connected on Sources (Apollo, RocketReach, People Data Labs, Hunter, SignalHire, Happenstance, SerpAPI, Clearbit, ContactOut, Lusha, ZoomInfo), in the order Lovie runs them. Give a name, the firm, and any email, phone or linkedin_url you already hold. Every candidate has passed a name check (and a phone check when looked up by phone) and carries its provider, what it was matched on, the attributes that agree and a confidence; attempts says which providers were asked, failed or are not connected. Nothing is saved: to record a value, propose it with fundraising_propose_change and let the member approve. Never present a candidate as confirmed. Each call can spend the company's provider credits, so look a person up once. Pass your agent_name. Read-only.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "connection_enrich_person"
  }
}

Input Schema

NameRequiredDescriptionDefault
firmNo
nameNo
emailNo
phoneNo
titleNo
locationNo
agentNameNo
companyIdNo
linkedinUrlNo
maxCandidatesNo

Output Schema

NameRequiredDescriptionDefault
attemptsNo
candidatesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only declare read-only/open-world; the description adds the material behavior: provider credit cost per call, nothing is persisted, candidates are post-name-check (and phone-check) with provider/match-basis/agreeing-attributes/confidence, and `attempts` reports which providers were asked, failed or are unconnected. That is real context an agent could not get from the annotations.

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 dense with information; nearly every sentence adds a distinct constraint (inputs, candidate guarantees, save workflow, credit warning, agent_name). The 11-provider enumeration is long but earns its place by telling the agent what sources are consulted.

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

Completeness4/5

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

An output schema exists, and the description still explains candidate shape and the `attempts` field, plus the approval workflow for persisting results. The remaining gap is the four undocumented input parameters, which matters for a 10-parameter tool with zero schema descriptions.

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 0% across 10 parameters, so the description must carry semantics. It names name, firm, email, phone, linkedinUrl and agentName ('pass your agent_name'), but title, location, companyId and maxCandidates are never mentioned, and no format or constraint guidance (lengths, patterns, the 0-10 candidate cap) is added.

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 ('finds contact details for one person') and enumerates exactly what it returns (email, phone, LinkedIn URL, title, company, photo). The multi-provider fan-out across the company's connected enrichment sources distinguishes it clearly from stored-contact readers like connection_list_dex_contacts or fundraising_get_network_person without needing to name them.

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 explicit inputs to supply ('a name, the firm, and any email, phone or linkedin_url you already hold'), an explicit do-not-repeat rule ('look a person up once' because calls spend provider credits), and routes the write path to a named alternative ('to record a value, propose it with fundraising_propose_change and let the member approve'). Also states the 'never present a candidate as confirmed' constraint.

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.