Markovo provides 11 tools with complete JSON Schema input definitions and descriptions for all tools and parameters. Naming follows verb_noun convention (markovo_convert, markovo_job_status, etc.). However, descriptions are terse (10-60 chars), lacking context on WHEN to use each tool, prerequisites, or recovery guidance. Output schemas are not documented, LLMs cannot predict response structure for chaining. Error handling is absent from descriptions. No tool annotations (readOnlyHint/destructiveHint). Parameter descriptions are minimal; e.g., 'Path to the input file to convert' lacks format/constraint details. No guidance on idempotency, retryability, or side effects.

• Add output schema documentation for all tools. Example: 'Returns {job_id: string, status: "queued"|"processing"|"completed"|"failed", created_at: ISO8601, result_url?: string}'.
• Expand tool descriptions to 50-200 chars with actionable context. E.g., 'markovo_job_status: Poll the status of a conversion job. Call this after markovo_convert to check progress. Returns status, progress %, and error details if failed.'
• Add tool annotations: mark markovo_convert and markovo_convert_url as destructiveHint=true (consume credits); mark read-only tools (markovo_job_status, markovo_usage, etc.) with readOnlyHint=true.
• Enhance parameter descriptions with format/constraint details. E.g., 'input_path: Path to input file (PDF, DOCX, PPTX, XLSX; max 256 MB; must be readable by the process).'
• Document error scenarios and recovery paths in tool descriptions. E.g., 'If conversion fails, check markovo_doctor to verify API key and service health, then retry.'