A Model Context Protocol server that fetches Kubernetes troubleshooting runbooks from https://containersolutions.github.io/runbooks/posts/kubernetes/
Three tools with basic verb-noun naming (search-, get-, list-) and descriptions present. However, descriptions are generic (10-50 chars), lack actionable context, and parameter descriptions are minimal. Input schemas visible but sparse: search-runbooks has 'query' and 'limit' with types and brief descriptions; get-runbook has only 'topic'; list-topics has empty input. No output schemas documented. No error handling guidance. No parameter constraints (e.g., limit bounds). Naming is clear but descriptions fail to explain WHEN to use each tool or what the LLM should expect in return. Baseline: avg tool description should be 194 chars; these are 30-60 chars.
Fetch a specific Kubernetes runbook by topic/slug
List all available Kubernetes runbook topics
Search through available Kubernetes runbooks by keyword or topic
Descriptions are too short (10-50 chars vs. baseline 194 chars). Missing WHEN to use each tool, what it returns, and how it differs from similar tools.
No output schemas documented. LLMs cannot plan downstream calls or extract required fields without knowing response structure.
Parameter 'limit' in search-runbooks lacks bounds (min/max). Unbounded integers let LLMs pass absurd values.
No error handling guidance. If a runbook is not found or network fails, LLM has no recovery path.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 44 | 2026-07-28+ | v2 |
list-topics has empty input schema (no parameters documented). Unclear if it accepts filters, pagination, or is truly parameterless.