axiorank_quarantine_agentReversible kill switch: quarantine an agent so the gateway DENIES all of its tool calls, or release it. Set quarantine: false to restore. Requires the agents:write scope.
| Name | Required | Description | Default |
|---|---|---|---|
| agentId | Yes | The agent's UUID (from axiorank_list_agents). | |
| quarantine | Yes | true = quarantine (deny all its calls); false = release. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses that quarantine denies all tool calls and that the action is reversible. Adds context beyond annotations (which mark destructive=true, idempotent=true) by specifying the gateway behavior and restore mechanism.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with the key metaphor and effect. Every word earns its place; no fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given simple params, no output schema, the description fully covers what the tool does, how to use it, and prerequisites. An agent can select and invoke correctly without ambiguity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions, but the description adds 'Set quarantine: false to restore' and connects agentId to the list_agents tool, providing practical guidance beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the verb (quarantine/release) and resource (agent), with a concise metaphor 'Reversible kill switch'. Distinguishes from siblings like revoke_agent by emphasizing reversibility.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly mentions required scope ('agents:write'), implying the tool should be used when you need to temporarily block an agent's calls. Lacks explicit contrast with revoke_agent, but context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct purpose, covering different aspects of agent, policy, incident, and threat management with no overlap. Tools like axiorank_list_agents and axiorank_get_agent are differentiated by list vs. get, and quarantine vs. revoke serve different use cases.
All tools follow a consistent 'axiorank_verb_noun' pattern in snake_case, making it easy to predict tool names based on action and resource. No mixing of conventions or abbreviations.
With 22 tools, the server covers a comprehensive security governance domain. While slightly above the typical 'well-scoped' range, each tool serves a specific function and the count is justified by the breadth of features (agents, policies, incidents, scoring, verification, audit).
The tool surface covers agent and policy lifecycle (CRUD except delete), incident querying, scoring, verification, and audit. Minor gaps include missing delete operations for policies and incidents, and no way to update incident status. However, the core workflows are well-supported.