The server provides 3 tools for Internet Archive access with HTTP transport, but suffers from incomplete schema documentation, missing parameter descriptions, and vague tool distinctions. Tool definitions exist in code but lack explicit JSON Schema registration visible in the provided source. Descriptions are present but generic. No error handling guidance, no parameter validation rules, and limited actionability for LLM recovery.

• Add explicit JSON Schema input definitions for all three tools. At minimum, specify parameter types, descriptions, and format constraints (e.g., date regex, URL format).
• Document output schema for each tool. E.g., webarchive_get_snapshot returns {text_content: string, snapshot_date: string, source_url: string}. webarchive_list_snapshots returns {snapshots: [{date: string, url: string}], total_count: number}.
• Add comprehensive descriptions to webarchive_list_snapshots and webarchive_search_snapshots. Clarify their distinct use cases: list_ for enumerate all snapshots of a URL; search_ for find snapshots by content/metadata query. State parameters, pagination, and limits.
• Add error handling guidance in descriptions: 'If page not found, try webarchive_list_snapshots to verify domain is archived. If domain not archived, no snapshots exist.'
• Document the cutoff_date environment variable and its precedence in tool descriptions, not just code comments.
• Consider merging list_ and search_ into a single tool with optional query/filter parameters, or clearly separate them (e.g., list_snapshots lists all; search_snapshots filters by date range or keyword).
• Add parameter constraints: target_date format (YYYY-MM-DD), URL validation, optional limit/pagination for list results.
• Expose rate limiting and timeout details in tool descriptions so LLM knows when to retry or escalate.
• Document the 50k character truncation in webarchive_get_snapshot's output schema or result description.