MaskMCP defines 4 tools with basic schemas and descriptions. All tools have input schemas with type definitions and descriptions present. However, descriptions are minimal (10-100 chars, well below the 194-char baseline), lacking context on WHEN to use each tool or dependencies. The mask_fetch tool has good parameter descriptions but lacks output schema documentation. No tool annotations (readOnlyHint, destructiveHint) despite all being read-only. Error handling is present but generic. Tool composition is reasonable (single responsibility), but descriptions do not guide LLM selection effectively.

• Expand tool descriptions to 100-200 chars. Example: mask_ping → 'Health check to verify the MaskMCP vault is running and responding. Call this first to confirm connectivity before using mask_fetch or mask_list_secrets.' This guides LLM selection.
• Add readOnlyHint: true to all 4 tools in the tool definition. This signals to LLMs that these calls are safe to retry and do not modify state.
• Document output schemas for mask_list_secrets (array of {alias, allowedDomains, updatedAt}), mask_has_secret ({exists: boolean}), and mask_fetch (JSON object with redacted secrets). Include in tool description or separate schema field.
• Enhance error messages with recovery guidance. E.g., 'Domain not in allowlist for this secret. Call mask_list_secrets to see which domains are allowed for this alias.'
• Add parameter descriptions for mask_fetch authType enum: 'How to pass the secret in the request. Header: adds Authorization header. Query: appends secret as URL parameter. Choose based on API requirements.'