Server has 4 tools with basic schemas and descriptions, but significant gaps limit production readiness. All tools have descriptions (10-80 chars, mostly adequate) and input schemas with types. However, parameter descriptions are sparse or missing context. Output schemas are not documented, LLMs cannot predict response structure. Error handling exists but lacks recovery guidance. No tool annotations (readOnlyHint, destructiveHint). Naming is clear and verb-driven (lint_*, get_*, validate_*), following conventions. Composition is reasonable, tools are single-purpose. Major weakness: output documentation and error messaging do not guide LLM recovery.

• Document output schemas for all tools. Add to tool descriptions: 'Returns: {summary: {exit_code, passed, profile_used, issue_count, error_count, warning_count}, issues: [{severity, message, details}], raw_output: {stdout, stderr}}'
• Enhance error messages with recovery guidance. E.g. 'Playbook exceeds 1MB limit. Try: (1) split into smaller files, (2) remove comments/whitespace, or (3) contact admin to increase limit.'
• Add profile descriptions to parameter docs. E.g. 'profile: basic (default, catches common issues) | production (strict, for CI/CD) | safety (security-focused) | test (minimal checks) | minimal (fastest)'
• Add tool annotations to schema. Mark all tools with readOnlyHint: true since they do not modify state. This signals to LLMs that retries are safe.
• Document get_lint_profiles response structure. E.g. 'Returns array of {name, description, rules_count}' so LLM knows what to expect.

Inferred effective spec: <=2025-11-25.

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