twelvebit Analytics

Create an alert

create_alert

Notify someone when a goal completes or a payment arrives. trigger: a goal name (see list_goals) or "payment". channel: email (target = an email address), or webhook, slack or discord (target = an https:// URL). At most 20 per site. Pass idempotency_key so that a retry does not add a second alert.

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": {
      "trigger": "<trigger>",
      "channel": "<channel>",
      "target": "<target>"
    },
    "name": "create_alert"
  }
}

Input Schema

Name	Required	Description
`site`	No	Site domain (example.com), id or public id (tb_…). Optional with a site key, or when the account has one site.
`target`	Yes
`channel`	Yes
`enabled`	No
`message`	No	Custom message. Same variables. Leave out for the default.
`subject`	No	Custom subject (email). Variables: {{goal}}, {{amount}}, {{country}}, {{source}}, {{path}}, {{site}}. Leave out for the default.
`trigger`	Yes
`idempotency_key`	No	A fresh UUID for this create. Send the same value when you retry the same call: the first result comes back and nothing is created twice.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Adds real operational context beyond the annotations: a hard quota of 20 alerts per site and a retry-safety contract via idempotency_key. This does not contradict idempotentHint=false, since safety comes from the caller-supplied key, not from inherent idempotency. It stops short of describing the response payload or whether channel/target validation failures surface as errors.

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

Conciseness5/5

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

Purpose is stated first, followed by compact per-parameter guidance, the quota, and the retry rule. Every clause carries information an agent would otherwise have to guess at.

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 an 8-parameter mutation with no output schema, the description covers the risky decisions: what trigger values are legal, what target must look like per channel, the quota, and how to retry safely. Remaining fields are self-evident or already documented in the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Coverage is 50%, and the description targets precisely the undocumented half: trigger, channel and target semantics, including the channel-dependent meaning of target (email address vs https:// URL). It adds nothing for enabled, message or subject, which the schema already describes.

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?

Opens with a concrete verb+resource+effect: alerting a person when a goal completes or a payment arrives. It names list_goals as the lookup for trigger values, but never contrasts itself with update_alert or list_alerts, so sibling routing is inferred from the tool name rather than stated.

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 the accepted trigger values (a goal name or "payment"), the four channel values with the target format each one requires, and the 20-per-site cap. It never says when to use this instead of update_alert or delete_alert, so the when-not side is absent.

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

All twelvebit Analytics tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?