MCP Tool

`nova.notifications_send`

For user artifacts, notices, and small work handoffs, an agent uses this public tool to check the state or evidence for "Notification Spoofing Guard". It explains which current signal can be used as evidence and when a follow-up step needs a fresh target check.

Agent tool

Canonical reference for a public MCP tool name.

Type: MCP tool
Family: Notifications
Effect: read-only
Status: Explained
Path: 18.12

Purpose

What this entry explains

What it does

nova.notifications_send An agent uses this tool to check the state or evidence for "Notification Spoofing Guard". It belongs to user artifacts, notices, and small work handoffs; agents should combine it with current discovery, target awareness, and the visible result.

Use when

Use this entry when an agent needs to check the state or evidence for "Notification Spoofing Guard" for user artifacts, notices, and small work handoffs.
Use it to understand the public tool name, its expected boundary, and the response signals to check.
Use it before chaining follow-up tools so the next step is based on current evidence.

Reference Use

How agents should cite and apply this area

Examples are maintained at family level and use only public tool names or reference paths already present in the catalog.

Family example

A task in user artifacts, notices, and small work handoffs can trigger powerful execution and therefore needs target, approval, and result check before the step.

The agent starts with nova.notifications_send, reads the current response or reference, and only then chooses the concrete next tool.

nova.notifications_send nova.notifications_list nova.notifications_unread_count

Current discovery, target, user control, warning signals, and result check come before execution.

Contract

Inputs and important response fields

This page is a public reference. Agents and integrators should still read current MCP tool discovery before execution, because schemas can be gated by settings or version.

Inputs

sourceKind

Public input field from the catalog source. Confirm the exact schema through current MCP discovery before execution.

Response fields

No fixed public response field is derived from the catalog source for this path. Use current tool discovery and the actual response before chaining the next step.

Safety

Boundary before execution

Effect

Reads current state or evidence. It should not be treated as permission to act without a fresh next-step check.

Agent rule

Use the response as current evidence, then choose a more specific next tool only after target, scope, and freshness are clear.

Human control

For humans, this entry explains what an agent reads in user artifacts, notices, and small work handoffs and which current signal should be checked before trusting the result.

Safety Axes

How this path can affect work

Axes are stable catalog signals for humans, agents, and LLM discovery. One path can carry several axes.

Read current state read_current_state

Reads current state, response signals, or evidence without treating that alone as permission for a follow-up action.

Use the signal as current evidence and re-check target, scope, and visible state before any follow-up action.

nova.notifications_send