Skip to main content
Glama

Import contacts

import_contacts
Destructive

Create or update up to 500 contacts per call, matched by phone_number. Attributes go in fields (up to 20 strings, e.g. plan) for segments and {{field:name}} merge tags; tags group contacts. opt_in carries consent evidence (status: false records an opt-out). import_id from the first response groups several calls; dry_run: true returns what would change and writes nothing.

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": {
      "contacts": "<contacts>"
    },
    "name": "import_contacts"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoA label for the import (first request only).
dry_runNotrue returns what would change and writes nothing
contactsYesContacts to create or update, up to 500 per call
import_idNoFrom a previous response, to group several requests as one import.
campaign_idNoApplies to every opt_in row that does not name its own campaign_id
check_line_typesNodry_run only. Looks up line types to count landlines; live lookups are paid, so only the first 500 numbers are checked.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changed
    • addedInput schema / properties / contacts / description
      Added value: +"Contacts to create or update, up to 500 per call"
    • addedInput schema / properties / contacts / items / properties / company / description
      Added value: +"Company name"
    • addedInput schema / properties / contacts / items / properties / email / description
      Added value: +"Email address"
    • addedInput schema / properties / contacts / items / properties / first_name / description
      Added value: +"First name"
    • addedInput schema / properties / contacts / items / properties / last_name / description
      Added value: +"Last name"
    • addedInput schema / properties / contacts / items / properties / notes / description
      Added value: +"Free-text notes"
    • addedInput schema / properties / contacts / items / properties / state / description
      Added value: +"US state or Canadian province, usually a 2-letter code"
    • addedInput schema / properties / contacts / items / properties / tags / description
      Added value: +"Labels that group contacts"
    • addedInput schema / properties / dry_run / description
      Added value: +"true returns what would change and writes nothing"
  2. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare this as a destructive, non-idempotent write. The description adds real operational context beyond that: the 500-contact cap, matching by phone_number, dry_run writing nothing, opt_in status=false recording an opt-out, and import_id grouping multiple calls. It does not discuss partial imports or skipped-row behavior except indirectly through schema details.

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 description is four dense sentences, front-loaded with the primary action and then key behavioral traits. It is efficient and has no filler, though the paragraph is packed with multiple concepts and could be easier to scan if structured.

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?

For a complex batch import with rich schema coverage and destructive annotations, the description covers the core operational concerns: batch size, matching, fields/tags, consent, import grouping, and dry_run. It falls short on error handling and full response expectations, though the import_id note partially offsets the lack of an output schema.

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 per-parameter schema already documents fields, opt_in, import_id, dry_run, and campaign_id in detail. The description restates the main semantics and adds only a little, chiefly that contacts are matched by phone_number, but mostly mirrors what the schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (create or update) and resource (contacts) with the batch limit and matching key. It does not name or distinguish itself from close siblings such as upsert_contact or bulk_update_contacts, so an agent still needs schema comparison to choose between them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies bulk contact import with consent evidence, fields, and dry-run previewing, and it explains import_id grouping. However, it never states when to use this tool versus upsert_contact, bulk_update_contacts, or import_opt_outs, and gives no when-not guidance.

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.