Single tool 'dripcheck_scan' has a reasonable description (127 chars, within 10-1024 range) but critical schema deficiencies. Input schema is minimal: only 'target' (string) with basic description, no type validation, format constraints, or examples. No output schema documented, LLMs cannot predict return structure. Parameter description lacks actionable detail (no format, range, or valid values). Tool name lacks action verb prefix (should be 'scan_email_sequence' or similar). No error handling guidance. No pagination, no structured output specification. Naming is vague, 'dripcheck_scan' does not clearly convey 'lint email deliverability' to an LLM unfamiliar with the domain.

• Rename tool to 'scan_email_sequence' or 'lint_email_deliverability' to start with an action verb and clarify intent without domain knowledge.
• Document the complete output schema: specify that the response is JSON with fields 'tool' (string), 'findings' (array of {id, severity, message, detail}), and 'score' (integer). Include example output.
• Expand 'target' parameter description to: 'Local file path or directory containing email sequence JSON files. Supports .json, .txt formats. Max 100MB. Returns error if path does not exist or is not readable.'
• Add error handling guidance to tool description: 'Returns error if target path is invalid, unreadable, or exceeds size limits. Errors are retryable. If permission denied, check file permissions and retry.'
• Add parameter constraints: specify accepted file formats, maximum file size, and whether the tool accepts directories (recursive scan) or single files only.