Skip to main content
Glama

Find contact info

create_enrichment

Looks up email, phone, and personal LinkedIn profiles for project ids this account already has. Does not browse the web, send email, or write to LinkedIn. Returns a job receipt only — enrichmentJobId, status, accepted, and skipped. Contact values are not in this response. On County, State, and National plans, costs 1 credit per project the first time this account receives an email, phone, or personal LinkedIn profile. The maximum is held when the job is queued, and unused credits are released. Names and company links alone do not add a charge. On API Only, included for records already purchased; unpurchased ids return in skipped.notPurchased. Empty lookups do not add a charge. Already-unlocked ids return in skipped.alreadyEnriched. Large lists are split into batches; the result lists leftover ids to pass as projectIds on the next call. get_enrichment returns job status. Once it is done, get_projects with the same projectIds and include="contacts" returns the contact values. A fresh project can take several minutes. A live trial includes 5 lookups, separate from record credits. For building permits pass permitIds in place of projectIds (at most 1,000 per call): it researches the companies and contractors each permit names and the people at them, at 1 credit per permit the first time it adds an email, phone, or personal LinkedIn profile the permit did not already print. Homeowners are never looked up; a permit naming only one returns in skipped.nothingToLookUp. Once the job is done, reading the permit again shows what was found under researchedParties.

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": "create_enrichment"
  }
}

Input Schema

NameRequiredDescriptionDefault
permitIdsNoBuilding permit ids, in place of projectIds. At most 1,000 per call. Tell the user how many lookups this can use before calling. A permit that names only a homeowner is skipped: private individuals are never looked up.
projectIdsNoPlanned project ids they already have. At most 1000. A long list starts in batches; pass leftover ids as projectIds on the next call. Pass this or permitIds, not both.

Output Schema

NameRequiredDescriptionDefault
statusNo
messageNo
enrichmentJobIdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations declare a non-read-only, non-idempotent, closed-world operation but say nothing about cost or side effects; the description fills that gap with credit pricing per plan, the hold-and-release mechanic, and which cases are free (names/company links, empty lookups, already-unlocked ids). It also states what the tool does not do (no web browsing, no email, no LinkedIn writes) and that the response is a job receipt rather than contact values, which prevents an agent from misreading the output.

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, exclusions, and return shape are front-loaded in the first three sentences, and every later sentence carries operational detail. It is nonetheless dense and runs long, with credit and skip rules compressed into prose that could be broken into clearer clauses, and some skip semantics duplicate the input schema.

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 an asynchronous, credit-consuming job-creation tool, the description covers cost, timing, batching, skip reasons, and the exact follow-up calls needed to retrieve results. An output schema exists, yet the description's clarification that the response is only a receipt (enrichmentJobId, status, accepted, skipped) is precisely the context an agent needs to avoid treating the call as returning contacts.

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 both parameters are already documented with types, bounds, and the mutual-exclusion rule, making 3 the baseline. The description does add real meaning beyond the schema, notably what permitIds actually researches (the companies and contractors each permit names, and the people at them), the per-permit credit basis, and the homeowner skip case, which edges it toward a 4 but largely restates schema content.

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 first sentence names a specific verb and resource: it looks up email, phone, and personal LinkedIn profiles for project ids the account already owns. It immediately distinguishes itself from get_enrichment (job status) and get_projects with include="contacts" (the actual values), so an agent can pick the right tool without opening a schema.

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?

It spells out the full workflow: call this, then get_enrichment for status, then get_projects with include="contacts" for values, and warns a fresh project can take several minutes. It also gives an explicit alternate mode (permitIds instead of projectIds) with its own conditions and the "pass this or permitIds, not both" rule, plus batch-overflow guidance for leftover ids.

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