Dialpad MCP server

dialpad_create_contact

Creates company-shared or user-local Dialpad contacts with names, phones, emails, and company details; admin approval is required before creation.

Instructions

Create a company-shared Dialpad contact (or a local contact for one user with owner_id). Same fields the N8N Autotask contact sync sends. Proposal: an administrator must approve it before it runs.

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": {
      "first_name": "<first_name>",
      "last_name": "<last_name>"
    },
    "name": "dialpad_create_contact"
  }
}

Input Schema

Name	Required	Description
`urls`	No	Web addresses. On update, replaces the whole list.
`emails`	No	Email addresses; the first is the primary. On update, replaces the whole list.
`phones`	No	Phone numbers in E.164 format; the first is the primary. On update, replaces the whole list.
`owner_id`	No	Make it a local contact of this user instead of a shared contact.
`extension`	No	Extension.
`job_title`	No	Job title.
`last_name`	Yes	Last name. The N8N sync appends the Autotask company short name, e.g. 'Smith ACME'.
`first_name`	Yes	First name.
`company_name`	No	Company name.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 14, 2026

TDQS

B3.4/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=true, so the safety profile is covered structurally. The description adds genuinely new behavioral context — an administrator must approve the call before it runs, which signals a delayed/blocked execution path — but says nothing about duplicate handling, error behavior, or what a successful creation returns, leaving real gaps for a mutation tool.

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?

Three short sentences, with the shared-vs-local scope distinction front-loaded. The middle sentence about the N8N Autotask sync is internal context of little use to a selecting agent, and the 'Proposal:' phrasing of the approval rule is awkward, but nothing is padded or repetitive.

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

Completeness3/5

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

For a 9-parameter mutation with no output schema, the description plus annotations plus full schema coverage give enough to call it correctly. What it omits — the returned contact identifier, duplicate/already-exists behavior, and whether the approval gate changes the response — are meaningful for a create tool with idempotentHint=false.

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 every parameter including owner_id, emails-primary semantics, and 'replaces the whole list' on update is already documented in structured data. The description's owner_id clause merely restates what the schema says, adding no new parameter meaning; baseline 3 applies.

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?

The description states a specific verb and resource ('Create a company-shared Dialpad contact') and distinguishes two creation modes — company-shared vs. local to a user via owner_id — which lets an agent separate it from dialpad_update_contact or dialpad_delete_contact. It does not explicitly name those siblings, but the create/update/delete split is unambiguous.

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?

It gives one real usage rule: pass owner_id to create a per-user local contact instead of a shared one. There is no guidance on when to prefer an update over a create, how duplicates should be handled, or what to do if the contact already exists, so the when-not side is missing.

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