Server has 7 tools with basic schemas and descriptions, but significant quality gaps. Tool names lack consistent verb-noun structure (e.g., 'run_command' is vague; 'browser' is a noun). Descriptions are present but generic (avg ~60 chars, well below 194-char baseline). Parameter descriptions exist but lack detail on constraints, formats, and valid ranges. No output schemas documented. Error handling and recovery guidance absent. Security concerns: 'run_command' and 'browser' accept arbitrary arguments without validation. No pagination support visible. Tools like 'login' and 'video_download' lack idempotency guarantees.

• Rename 'browser' → 'execute_browser_command' and 'run_command' → 'execute_adapter_command' to follow verb_noun pattern and clarify intent.
• Document output schema for each tool. E.g., search returns {results: [{id, title, url, source}], total_count, has_more}. Include all fields LLMs need for chaining.
• Add constraint descriptions to 'args' parameters: 'Valid keys depend on site and command; call site_help(site) to list available commands and their arguments.'
• Add error handling guidance: 'If login times out, increase timeout or verify site is accessible. If video_download fails, check URL is valid and quality is available.'
• Implement idempotency for video_download: accept optional 'request_id' parameter; return same result if called twice with same request_id within 24 hours.

Inferred effective spec: 2026-07-28+.

• Relies on Logging (deprecated) - log to stderr or use OpenTelemetry