新建文章

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

With no annotations, the description carries full burden and discloses critical behaviors: default mode is draft, publish is irreversible and cannot revert to draft, published articles can only be deleted and recreated, markdown is rendered to HTML while retaining source, tags are capped at 5, and description is auto-generated when omitted. This goes well beyond basic 'create' semantics.

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?

The description is dense and information-rich, with the core purpose front-loaded and the most important warning about irreversibility placed early. Every sentence contributes either parameter semantics, behavioral warnings, or usage exclusions; there is no filler or repetition.

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?

Given no annotations, no output schema, and eight parameters, the description covers the most safety-critical aspects and common usage pitfalls thoroughly. It omits return-value behavior and a few parameter details, but the description provides sufficient context for an agent to invoke the tool correctly in the main workflows.

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?

Schema description coverage is 0%, so the description must compensate. It adds meaning for mode (default draft, publish semantics), markdown (source stored and rendered), tags (max 5), and description (auto-generation). However, it does not explain verify, categories, or cover_image, leaving some parameters only minimally understood through the schema.

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 states a specific verb and resource: creating a new article and saving it to CSDN. It also explicitly distinguishes itself from updating existing articles ('不要用它更新已有文章（那会新建一篇）'), which differentiates it from the sibling update_article.

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 gives explicit when-to-use guidance: keep the default draft mode when review is needed. It also provides clear when-not-to-use exclusions: do not use it to update existing articles and do not pass mode=publish as a test, because publishing is irreversible.

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