Check active coercion and systemic failure clusters to avoid hostile environments. Returns clustered warnings of malicious prompts before executing risky tools.
Check active systemic failure and coercion clusters before executing risky tools. Returns clustered warnings of coercion, malicious prompts, or hostile environments.
| Name | Required | Description | Default |
|---|---|---|---|
| status | No | Cluster status filter | ACTIVE |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full disclosure burden. It discloses the return content (clustered warnings of coercion, malicious prompts, hostile environments) and positions itself as a pre-execution check, which implies a read-only operation. It does not state whether the tool is advisory or blocking, what happens when no alerts exist, or whether any side effects occur.
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 with zero filler; the first sentence front-loads the purpose and trigger condition, the second states the return content. Every clause earns its place and the description is immediately scannable.
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?
For a tool with one optional, fully-documented parameter, the core mechanics are covered: what it checks, when to call it, and what it returns. Gaps remain because there is no output schema and the description does not explain empty-result behavior, warning severity, or recommended follow-up actions after warnings are returned, which matters for a safety-gate tool.
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% and the status parameter is fully documented in the schema with an enum, a default value, and a 'Cluster status filter' description. The description adds no additional meaning about the status filter or how filtering interacts with the returned clusters, so the baseline 3 for high schema coverage applies.
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?
The description states a specific action ('Check') applied to a concrete resource ('active systemic failure and coercion clusters') and specifies the return value ('clustered warnings of coercion, malicious prompts, or hostile environments'). This clearly conveys that the tool is a safety pre-flight query. It does not explicitly contrast sibling tools such as subctx_injustice_browse, so differentiation relies on the reader inferring that 'query_alerts' is a check rather than a browse.
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?
The phrase 'before executing risky tools' provides an explicit trigger condition that tells an agent when to invoke this tool, which is clear contextual guidance. However, it names no alternative tools and gives no when-not-to-use conditions, leaving the relationship to read-oriented siblings like subctx_injustice_browse implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.