evidence_gap_scan

What evidence_gap_scan does on Nodebench

AI agents call evidence_gap_scan to retrieve information from Nodebench without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why evidence_gap_scan is rated Low

This tool performs a scan to list or report on missing evidence, which is a read-only operation. It retrieves or reports status information relevant to diligence preparation. No data is modified, executed, destroyed, or financial commitments are made. The blast radius of misuse is minimal—an agent could generate inaccurate reports of missing evidence, but cannot cause system damage or data loss.

From the tool's definition Tool name 'evidence_gap_scan' and description 'List missing evidence classes and materials for diligence readiness' indicate a query/retrieval operation that identifies gaps in evidence documentation without modifying, executing, or deleting anything.

The rule that runs evidence_gap_scan safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Nodebench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For evidence_gap_scan, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "evidence_gap_scan": {}
  }
}

Questions about evidence_gap_scan