Skip to main content
Glama
pushengage-mcp

pushengage-mcp

Delete a notification

pushengage_delete_notification
DestructiveIdempotent

Deletes a draft, scheduled, or recurring notification to cancel a pending send before it goes out. Use it to stop unnotified campaigns, including undelivered subscriber-timezone sends and full A/B tests.

Instructions

Deletes a draft, scheduled or recurring notification, cancelling it if it had not gone out yet. A notification that has already been sent CANNOT be deleted — its delivery record is kept — and neither can an RSS auto-push notification. Deleting the PARENT of an A/B test removes the whole test including its other variant; a single variant cannot be deleted on its own, and neither can a drip, triggered or single-timezone notification. For a subscriber-timezone send this also removes the per timezone notifications that have not been delivered. This cancels a pending send, so confirm with the user before calling it.

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": {
      "notification_id": "<notification_id>"
    },
    "name": "pushengage_delete_notification"
  }
}

Input Schema

NameRequiredDescriptionDefault
site_idNoOverride the currently selected site
notification_idYesThe notification to act on. Get it from pushengage_list_notifications, or from the notification_id a send tool returned.

Output Schema

NameRequiredDescriptionDefault
deletedNo
deleted_countNo
notification_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.2.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare destructive=true, idempotent=true and openWorldHint=true, so the safety profile is covered; the description builds on that with consequences the annotations cannot express — delivery records are retained, deleting an A/B parent wipes the sibling variant, and undelivered per-timezone notifications are removed. This is genuine behavioral disclosure, not repetition of structured fields.

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?

Dense with constraints but every clause rules out a distinct failure mode, and the core action plus the primary cannot-delete rule are front-loaded in the first two sentences. It runs long, yet the length is earned by the breadth of exclusions a destructive tool must communicate.

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 an output schema present and full schema description coverage, the description need not explain return values and instead spends its budget on the edge cases an agent would otherwise get wrong (A/B parents, timezone fan-out, sent notifications). Nothing material for correct invocation is missing.

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?

Schema coverage is 100% and both parameters are documented in-schema, so the baseline is 3; the description earns a small bump by clarifying that notification_id can refer to an A/B parent (with the cascade consequence that implies) and by pointing to pushengage_list_notifications as the id source.

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?

Opens with a specific verb and resource ("Deletes a draft, scheduled or recurring notification") and immediately narrows the scope to three deletable states, so an agent can tell this apart from update/duplicate/resend siblings without opening a schema.

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

Usage Guidelines5/5

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

Supplies explicit when-not conditions: already-sent notifications, RSS auto-push, A/B test variants individually, drip, triggered and single-timezone notifications are all undeletable. It also adds an operational guardrail, "confirm with the user before calling it," which is exactly the usage guidance a destructive tool needs.

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