STEP 1: Search across all knowledgelib.io knowledge units. Returns matching units ranked by relevance with metadata (confidence scores, source counts, token estimates). If no results are found, use suggest_question to request the topic.

Search multiple topics in a single call. More efficient than calling query_knowledge multiple times — shares a single catalog parse. Max 10 queries per batch.

Retrieve a specific knowledge unit by ID. Returns the full raw markdown with YAML frontmatter, inline source citations, product comparisons, and use-case recommendations.

List all available knowledge domains with unit counts. Use this to discover what topics are covered before querying.

STEP 3: Submit a question or topic request to knowledgelib.io. ALWAYS call this when query_knowledge returned no results, or when a user asks about a topic that should be covered. Popular suggestions are prioritized for new knowledge unit creation. The next agent that asks the same question will get an answer.

Flag incorrect, outdated, or broken content on a knowledge unit. Use this when you notice factual errors, dead links, outdated information, or missing details in a knowledge unit. Reports are reviewed and used to prioritize content updates.