Skip to main content
Glama

Add a notification contact

add_notification_contact

Adds an email address, chat channel, paging service, Jira project, webhook or phone number to alert on outages and recoveries. Email contacts must open a confirmation link before they receive alerts. A phone number texts or calls through the user's own account with a provider, on every plan, which bills them: twilio (Account SID, Auth Token) and plivo (Auth ID, Auth Token) text or call, vonage (API key and secret) and telnyx (API key) text. The user gives you the credentials and the sender, one of the account's numbers or for texts a sender ID of up to 11 letters and digits (not in the US or Canada). It needs no code: check it with test_notification_contact. sms and voice, through UpHeron's own Twilio account, are no longer added.

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": {
      "name": "<name>",
      "kind": "<kind>",
      "destination": "<destination>"
    },
    "name": "add_notification_contact"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYesEvery plan alerts by email and through your own account with a texting provider, which bills you: `twilio` and `plivo` text or call, `vonage` and `telnyx` text (no code to confirm, send a test instead); the other kinds need a paid plan (pay-as-you-go workspaces: email, webhook, twilio, vonage, plivo and telnyx). `sms` and `voice`, texts and calls through UpHeron's own Twilio account, are no longer added (422 `phone_kind_retired`); contacts added before keep working and confirm with a code (`/alert-channels/{id}/confirm`). Push notifications to a device are added in the dashboard.
nameYesYour name for the contact, such as "Ops email".
tokenNoTelegram bot token, Pushover application token, ntfy access token (optional), Jira API token, Twilio or Plivo Auth Token, Vonage API secret, Telnyx API key, or a webhook's signing secret (optional: `whsec_` and 24 to 64 bytes in Base64; one is made when it is left out). Stored encrypted and never returned, except a webhook's signing secret as `signing_secret` in the response that made it.
optionsNoopsgenie: `region` (us or eu, default us). splunk_oncall: `routing_key`. jira: `email` (the account the API token belongs to), `project` (key, such as OPS), `issue_type` (default Task) and `resolve_status` (optional: the status a resolved incident's issue moves to, such as Done). twilio: `account_sid` (AC…), `from_number` and `mode` (sms or call, default sms). vonage: `api_key` and `from_number`. plivo: `auth_id` (MA… or SA…), `from_number` and `mode`. telnyx: `from_number` and `messaging_profile_id` (needed for a sender ID; without `from_number` the profile's numbers send). `from_number` is one of the account's numbers with its country code, or for texts a sender ID of up to 11 letters, digits and spaces with at least one letter (not accepted in the US and Canada), or for twilio a Messaging Service SID (MG…).
destinationYesEmail address; webhook URL (slack, discord, teams, google_chat, mattermost, rocketchat, ntfy, webhook, zapier: its Catch Hook URL); Telegram chat ID; PagerDuty or ilert integration key, Pushover user key or Opsgenie API key; Splunk On-Call REST endpoint URL; Jira site URL (https://your-team.atlassian.net); or for twilio, vonage, plivo and telnyx the phone number to alert, with its country code (+359…).
error_typesNoAlert about the outages of these kinds of errors only, and their recoveries; null or left out for every kind. timeout, connection (refused, reset, unreachable, no reply), dns, tls (handshake and certificate verification), http_5xx, http_4xx, http_status (other unexpected statuses), content (missing text, a failed JSON assertion, a wrong reply), slow (latency threshold, performance score), heartbeat (missed or failed runs), expiry (certificate and domain monitors) and other. Expiry reminders, vulnerability and port alerts are not filtered.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / name / description
      Added value: +"Your name for the contact, such as \"Ops email\"."
  2. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations only declare it is a non-idempotent, non-destructive open-world write. The description adds real behavior beyond that: email contacts must open a confirmation link before alerts flow, phone contacts bill the user through their own provider account, and retired kinds return 422 phone_kind_retired. It does not describe failure modes such as duplicate contacts or validation errors for bad credentials.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded and the confirmation/billing notes are valuable, but the long sentence enumerating twilio/plivo/vonage/telnyx credentials duplicates the schema verbatim and bloats the paragraph. The trailing note about retired sms/voice appears after the detail rather than up front.

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 6-parameter mutation with a nested options object and no output schema, the description covers the confirmation flow, billing implications, alternatives for testing, and the one response field worth knowing (a webhook signing_secret). It omits what a successful creation returns otherwise (e.g. the contact id) but the schema carries the rest.

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 every parameter including the per-kind options object. The description largely restates schema content (provider credential names, from_number/sender ID rules) rather than adding new meaning, so the baseline of 3 applies.

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 (adds) and an enumerated resource set (email, chat channel, paging service, Jira project, webhook, phone number) plus the goal (alert on outages and recoveries). An agent can immediately tell this is the creation tool for alert contacts, distinct from list_notification_contacts or test_notification_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?

Explicitly routes validation to test_notification_contact ("check it with test_notification_contact") and warns that sms/voice kinds are retired and will 422. It does not say when to prefer confirm_notification_contact or how to handle duplicates, but the primary when-to-use context is clear.

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