Skip to main content
Glama
wuapidev

wuapi MCP server

Official
by wuapidev

Save contacts on the phone

save_contacts
Idempotent

Save WhatsApp contacts to the linked phone and its address book, individually or in batches of up to 500, while queued sync reports pending, synced, or failed status.

Instructions

Save contacts on the linked phone, in WhatsApp and in the phone's own address book, as if they were saved on the phone. Any number can be saved. Saves are queued (also while the account reconnects): each contact's phoneSync says pending, then synced or failed (not_on_whatsapp, account_offline), and contact.updated fires; the phone shows the name about a minute later. Removing a contact is not supported. backfill_auto_save queues the contacts of the account's existing direct chats, named with its auto-save templates (update_account contactAutoSave), at most 200 a day.

Actions:

  • one: Save one contact under savedName. Returns the contact with its phoneSync.

  • many: Save up to 500 contacts at once. Returns the batch id and each contact's status.

  • backfill_auto_save: Queue the auto-save of the contacts of the account's existing direct chats.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYesWhat to do. See the list of actions in the tool description.
contactsNo1 to 500 contacts to save. Required for `many`.
accountIdNoThe wuapi account id of the linked number to act as (from list_accounts). Required for every action.
contactIdNoA contact: E.164 with + (`+584241112233`) or `lid:<digits>`. Required for `one`.
firstNameNoThe short name the phone shows. Defaults to the first word of `savedName`. Optional for `one`.
savedNameNoThe name to save the contact under. Required for `one`.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.14.0

TDQS

A4.4/5.0
Behavior5/5

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

Adds substantial behavior beyond annotations: the queued async model, the phoneSync lifecycle (pending → synced/failed with not_on_whatsapp / account_offline reasons), the contact.updated event, the ~1 minute propagation delay, and the 200/day backfill cap. This is exactly the context an agent needs to avoid assuming synchronous completion.

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-loads the core behavior before the action list, and the bulleted actions are easy to scan. The prose paragraph is dense with parentheticals and could be trimmed slightly, but every sentence carries real information.

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?

With no output schema, the description correctly steps in to describe return values (contact with phoneSync, batch id and per-contact status), plus the async lifecycle and limits. Nothing an agent needs to invoke this correctly is missing.

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 documents contactId formats, required/optional fields, and per-action requirements. The description reinforces a few of these (savedName for `one`, batch semantics for `many`, auto-save templates for backfill) but adds little the schema doesn't already say, so the baseline 3 holds.

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+resource (save contacts) and precisely where they land: the linked phone, WhatsApp, and the phone's address book. This clearly separates it from siblings like lookup_contacts, get_contact, and send_contact.

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?

Gives clear operational context (any number can be saved, saves are queued even while reconnecting, removal is not supported) and enumerates the three actions with their intent. It doesn't explicitly route to an alternative sibling tool for deletion or verification, but the 'removing is not supported' exclusion covers the main boundary.

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