Single tool k8saudit_scan has a basic description but critically lacks parameter descriptions and output schema documentation. The input schema defines 'target' as a string but provides no guidance on format, constraints, or examples. No output schema is documented despite the tool returning JSON findings. Parameter descriptions are absent entirely. The tool name follows verb_noun convention (audit action), but the implementation lacks the rigor expected for production agent use.

• Add parameter description to 'target': 'Path to a Kubernetes manifest file or directory. Accepts absolute or relative paths. Recursively scans directories for .yaml/.yml files. Example: /path/to/manifests or ./k8s'
• Document the output schema in the tool description or as a structured comment: Returns {tool: string, findings: [{id: string, sev: string, where: string}], score: number}
• Expand tool description to 150-200 chars: 'Audit Kubernetes manifests against CIS Kubernetes Benchmark security rules. Scans YAML files for misconfigurations (e.g., missing resource limits, privileged containers). Call this first to identify security gaps before deployment.'
• Add error handling guidance: 'If path not found, verify the file/directory exists and is readable. If YAML parsing fails, check manifest syntax. If no findings returned, manifests may already comply with CIS rules.'
• Migrate from STDIO to HTTP+SSE or Streamable HTTP transport to enable remote client access and hosted deployment.