Two tools with basic schemas and minimal descriptions. read_wechat_article and view_wechat_image both have single string parameters with type definitions, but descriptions are extremely terse (under 50 chars each). No output schemas documented. No error handling guidance. No parameter constraints (enums, ranges). Tool names follow verb_noun pattern but lack clarity on what 'read' vs 'view' return. No idempotency hints or destructive operation markers. Security validation is strong (SSRF checks, domain whitelist) but not exposed in tool descriptions.

• Expand tool descriptions to 100-200 characters. Example: 'read_wechat_article: Fetch a public WeChat Official Account article by URL and extract its text, headings, and image references as markdown. Returns {title, author, publish_time, body, images}. Requires URL starting with https://mp.weixin.qq.com/s/'
• Document output schemas explicitly. Add to tool description or a separate schema field: 'Returns {title: string, author: string, publish_time: string, body: string, images: [{index: int, url: string, alt: string}]}'
• Add parameter constraints to descriptions. Example: 'url (string, required): WeChat article URL. Must start with https://mp.weixin.qq.com/s/ and be publicly accessible. Invalid URLs return error with guidance.'
• Add tool annotations to FastMCP tool registration. Mark both tools with readOnlyHint=true and idempotentHint=true so LLMs know they are safe to retry.
• Document error cases and recovery paths. Example: 'If URL validation fails, error message will specify which constraint was violated (invalid domain, unreachable host, etc.) and suggest checking the URL format.'