Find leaked cloud keys (AWS/GCP/Azure) + classify blast radius
Single tool 'cloudkeys_scan' has a basic description (67 chars) but critically lacks parameter descriptions. The input schema defines 'target' as a string with a description ('File or directory path to scan for leaked cloud keys'), which is present but minimal. No output schema is documented, the tool returns JSON but the structure is not formally specified. The tool name follows verb_noun convention (scan), which is good, but the overall definition is sparse and would not meet production standards for LLM-driven agent selection.
Find leaked cloud keys (AWS/GCP/Azure) + classify blast radius. Returns JSON findings.
No output schema documented. Tool returns JSON findings but structure (fields, types, nesting) is not formally specified. LLMs cannot plan downstream operations or extract fields reliably.
Parameter 'target' description is minimal (47 chars). Does not specify format constraints (file vs directory vs both), size limits, or error cases (nonexistent path, permission denied). LLMs cannot validate input before calling.
Tool description (67 chars) lacks context on when to use it vs alternatives, prerequisites, or what 'blast radius' classification means. Does not explain output structure or error handling.
No error handling guidance. Tool may fail on nonexistent paths, permission errors, or invalid input, but no recovery hints are provided. LLMs will not know what to do on failure.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 52 | 2026-07-28+ | v2 |
STDIO transport only. Server is not remotely accessible and cannot be used by hosted MCP clients. Limits deployment to local/CLI-only scenarios.