Server has 7 tools with consistent naming (verb_noun pattern: doctor, hub_status, list_projects, get_jobs, get_job_detail, get_analytics, enqueue_job). All tools have descriptions (avg ~80 chars, within baseline). Input schemas are present and typed for all tools. However, descriptions are terse and lack WHEN/WHY guidance. Parameter descriptions exist but are minimal. Output schemas are not documented in the source. Error handling is basic (no recovery guidance visible). No tool annotations (readOnlyHint/destructiveHint). Overall: functional but below production bar.

• Document output schemas for all tools. E.g., list_projects should return {projects: [{id, slug, name, path, provider, added_at, last_seen_at}], total: number}. This enables chaining and LLM planning.
• Expand tool descriptions to 100-150 chars with WHEN/WHY guidance. E.g., 'Check if specrails-hub is running and accessible. Call this first if list_projects or enqueue_job fails, or to verify hub connectivity before batch operations.'
• Add tool annotations: mark doctor, hub_status, list_projects, get_jobs, get_job_detail, get_analytics with readOnlyHint=true. Mark enqueue_job with destructiveHint=true (or idempotentHint if retryable).
• Enhance parameter descriptions with format/constraint guidance. E.g., enqueue_job.command: 'Command to run (e.g., "implement", "health-check", "product-backlog #42"). See specrails-core docs for full command list.'
• Add error recovery guidance in tool descriptions. E.g., hub_status: 'If this fails, check ~/.specrails/hub.sqlite exists and hub server is running on localhost:4200.'