Skip to main content
Glama

ai_kill_switch

DestructiveIdempotent

Immediately disable AI agents, agentic workflows, or Now Assist skills for all users, check on/off status, and restore them when needed.

Instructions

AI Control Tower containment for one AI agent, agentic workflow or Now Assist skill. action=status reads its on/off state. action=contain switches it OFF right away for every user and channel (sn_aia_agent_config.active, sn_aia_usecase_config_override.active or sn_nowassist_skill_config.active = false). action=restore switches it back ON. The reason is written as a work note on its AI Control Tower asset when one exists. These records are application files: the change is captured in your current update set, and on a store-delivered agent or skill it marks the file as customized, which stays after restore (revert to the store version if upgrades must apply). AI Control Tower containment (Deactivate Agent / Reinstate on the AI asset, Brazil and later) is a UI feature with no documented REST API, so this flips the same active flags that AI Agent Studio and Now Assist Admin use. It does not revoke access in external platforms. Contain and restore REQUIRE WRITE_ENABLED=true, confirm=true and a reason.

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": {
      "action": "<action>",
      "target": "<target>"
    },
    "name": "ai_kill_switch"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYesWhat to do
reasonNoWhy (required for contain and restore; recorded on the AI asset)
targetYessys_id or name of the agent, workflow or skill
confirmNoMust be true for contain and restore
target_typeNoagent (AI agent), workflow (agentic workflow / use case) or skill (Now Assist skill). Default agent.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv5.0.1

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare destructiveHint and idempotentHint, but the description adds substantial context beyond them: the exact fields flipped (sn_aia_agent_config.active, sn_aia_usecase_config_override.active, sn_nowassist_skill_config.active), the every-user/every-channel blast radius, update-set capture, the persistent 'customized' marker on store-delivered assets after restore, and the recoverability caveat about reverting to the store version. That is exactly the extra disclosure a destructive mutation needs.

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?

Purpose is front-loaded and each sentence carries distinct information (action semantics, field mapping, caveat, API rationale, prerequisites). It is dense and slightly long, with parenthetical field lists that slow scanning, but there is little true redundancy.

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 a destructive, cross-channel kill switch with no output schema, the description covers state semantics, blast radius, persistence side effects, prerequisites, and limits (no external revocation). An agent has everything needed to decide and invoke correctly.

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 description coverage is 100%, so baseline is 3; the description goes further by giving each action's runtime meaning and by explaining that the reason is written as a work note on the AI Control Tower asset when one exists, which is not in the schema. It does not add format guidance for target resolution beyond what the schema already says.

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?

The description opens with a specific verb and resource ('AI Control Tower containment for one AI agent, agentic workflow or Now Assist skill') and then enumerates the three actions and their exact effects. No sibling tool in the catalog performs containment, and the status/contain/restore split makes the tool's scope unambiguous.

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?

It explains the operating context clearly: AI Control Tower containment is a UI-only feature with no documented REST API, so this tool flips the same active flags used by AI Agent Studio and Now Assist Admin, and it explicitly does not revoke external-platform access. It also states prerequisites (WRITE_ENABLED=true, confirm=true, reason). It stops short of naming an alternative tool or explicitly saying when *not* to use it.

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

Deploy Server

Other Tools