get_media_info

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description takes on full disclosure responsibility. It reveals type-dependent outputs: '对微信文章/网页/文件类，返回可访问 URL；对笔记类（media_id 以 note_ 开头），会自动拉取并返回笔记正文' (for WeChat/web/file returns accessible URL; for notes starting with note_ automatically fetches and returns note_content). It also names the field note_content and states plain text. It doesn't mention authorization or error handling, but the behavioral core is transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences deliver the purpose, source of the parameter, and type-specific behavior with no redundancy. The main verb and resource appear first, and conditional behavior is compactly described.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter tool with no output schema, the description covers the essential return distinctions (URL vs note_content) and the provenance of the ID. It is sufficiently complete for invocation, though it might have been strengthened by noting the absence of download links for note types or potential errors, but these are minor gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema only defines media_id as '媒体条目 ID', but the description adds crucial context: it explains the media_id originates from get_knowledge_list or search_knowledge, and that the note_ prefix changes the tool's behavior. This meaningfully extends the bare schema definition.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a clear verb-object phrase '获取知识库条目的原文内容或下载链接' (get original content or download link of knowledge base entry), specifying both action and resource. It distinguishes from siblings by detailing type-specific behaviors (URL for articles/web/files vs note_content for notes), which differentiates it from get_note_content and get_knowledge_list.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description instructs to pass media_id obtained from get_knowledge_list or search_knowledge, establishing a clear prerequisite. It explains type-based branching (note_ prefix vs others), giving contextual guidance on what to expect. However, it doesn't explicitly contrast with the sibling get_note_content or state when not to use this tool, so it misses explicit exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.