Skip to main content
Glama

Build a contact list

build_list
DestructiveIdempotent

Buys the list priced with quote_list: same filters and count, plus max_credits, the most the person agreed to spend. Reveals the businesses in order of record quality, never spends more than max_credits (businesses already revealed come free) and returns one row per business (WhatsApp with its wa.me link, mobile, phone, email, website, place, when the contact was last seen) plus a receipt: delivered, charged, free, how many have WhatsApp, credits per WhatsApp and credits left. Only businesses with at least one contact are listed; to pay only for WhatsApp, set channel: 'whatsapp'.

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": {
      "count": "<count>",
      "max_credits": "<max_credits>"
    },
    "name": "build_list"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoPart of the business name
countYesHow many businesses the list should have (max 200)
placeNoProvince, canton or district in Costa Rica (e.g. 'Escazú', 'La Fortuna', 'Heredia'); in Panama, province, district or corregimiento (e.g. 'Chiriquí', 'David', 'Bella Vista'); in Guatemala, department or municipality (e.g. 'Quetzaltenango', 'Mixco'); in the Dominican Republic, province or municipality (e.g. 'La Vega', 'Santo Domingo Este'). Accents optional
socialNoOnly businesses with this social profile
bookingNoHow they take bookings: through WhatsApp, without a booking system (phone, email, form) or with one. Known for about 1,500 businesses, mostly spas, salons and hotels
channelNoOnly businesses with this contact (mobile: a mobile number published as a phone, likely WhatsApp)
countryNoCR (Costa Rica, the default), PA (Panama), GT (Guatemala) or DO (Dominican Republic)
websiteNonone: no website (or it is down or parked); has: a working website
ad_pixelNotrue: its own website has a Meta or TikTok ad pixel
categoryNoCategory slug inside the industry, e.g. barberia, odontologia, pulperia_minisuper, taller_mecanico, hotel. list_categories has them all; an unknown one comes back with the valid ones
industryNoIndustry slug, named in search_businesses and list_categories
min_roomsNoHotels: at least this many rooms
built_withNoOnly businesses whose own website is built with this CMS or site builder
email_typeNoown_domain: email on the business's own domain; free: Gmail, Hotmail, Outlook, Yahoo, iCloud and similar
max_creditsYesThe most credits the person agreed to spend in this call
online_storeNotrue: its own website is an online store (Shopify, WooCommerce with products, PrestaShop…)
outdated_siteNotrue: its own website shows no update in two years or more (copyright year or page dates)
independent_onlyNotrue: small businesses only, no chain locations
min_whatsapp_confidenceNoMinimum WhatsApp confidence, 0 to 1

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the annotations, it discloses the economically critical behaviors: ordering by record quality, a hard spend ceiling via max_credits, that previously revealed businesses are free, that only businesses with at least one contact appear, and the exact contents of the per-business row and receipt. This is unusually thorough for a credit-spending, destructiveHint=true mutation.

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?

The spending ceiling and free-rereveal rules are front-loaded before the return-value inventory, which is the right order for a costly operation. The long parenthetical enumerating contact fields is dense but earns its place by replacing an absent output 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 a 19-parameter, credit-spending tool with no output schema, the description covers cost mechanics, ordering, filtering guarantees, row contents, and receipt fields. An agent has everything needed to call it safely and to interpret the result.

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 nearly all parameter meaning is already in the schema. The description adds only the framing of max_credits as the agreed spend cap and the tip that channel: 'whatsapp' limits payment scope; the remaining 17 filters are referenced collectively as 'same filters' rather than explained.

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 a specific verb and resource ('Buys the list priced with quote_list') and immediately positions it against the sibling that prices the same filters and count. Its add-on, 'plus max_credits', tells an agent exactly what distinguishes buying from quoting.

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 clearly frames the buying step as following quote_list with the same filters and count, and gives a concrete conditional ('to pay only for WhatsApp, set channel: whatsapp'). It stops short of explicitly warning against buying without a prior quote or distinguishing itself from reveal_contacts/match_list, so the when-not guidance is only implied.

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