新建草稿

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

With no annotations at all, the description still discloses substantive traits: it produces a draft (not a published article) and returns a media_id, and by default it uploads inline images to WeChat and rewrites their links. That side effect is exactly the kind of behavior an agent needs to know before calling. It omits draft-count quota limits and any auth requirements.

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?

Three compact clauses: purpose and return value first, then content-format behavior, then cover options. It stays front-loaded and wastes little, though the cover sentence overlaps with the schema's 二选一 note.

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 create tool with no annotations, no output schema, and a fairly rich nested article schema, the description covers the essentials: what is created, what is returned, and the default image-localization behavior. Missing quota/limit information and confirmation that nothing is published immediately leaves a small gap, but the agent can call it correctly.

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 100% and the nested article fields are all documented, so the schema does the heavy lifting. The description echoes a few of those fields (Markdown body, automatic image localization, cover alternatives) but adds no syntax or format detail beyond what the schema already says.

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 names a specific verb and resource (新建图文草稿), notes support for multiple articles, and states the return value (草稿 media_id). An agent can distinguish it from wechat_update_draft or wechat_publish_draft by the word 新建, though no sibling is named explicitly.

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 implies a creation workflow and clarifies the cover-image choice between thumb_media_id and thumb_image, which helps with one decision. It never states when to prefer this over wechat_update_draft or wechat_publish_draft, and gives no prerequisites such as account or IP-whitelist requirements.

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