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

Annotations only supply readOnly=false, destructive=false, openWorld=false — a bare safety profile. The description adds real behavioral context beyond that: the output is a non-public draft, the draft expires in 1 hour (草稿 1 小时内有效), and a second call is required to go live. It stops short of covering draft quota, cleanup, or whether a draft can be discarded, so it is strong rather than exhaustive.

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?

Front-loaded with the single most decision-relevant fact (this creates a private draft), then per-parameter notes, then the expiry caveat. Sentences are dense but purposeful; a couple of clauses (5000 字 / 最多 3 张) duplicate the schema and could be trimmed.

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?

With no output schema, the description still names the one return value that matters for chaining (draft_id) plus the 1-hour validity window, and it covers the non-obvious image-reference handling rule. Minor gaps remain around other returned fields and draft lifecycle, but an agent has enough to call and chain 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 coverage is 100%, so baseline is 3; the description adds value by explaining that place is geocoded (会解析成地图位置) and that the post then surfaces at that location, and by warning not to fabricate download_url values for images. It loses a point for restating limits already in the schema (5000 字, 最多 3 张) and for saying 正文和图片至少要有一样, which is looser than the schema's required:["content"] and could leave an agent unsure whether content may be omitted.

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?

States a specific verb and resource (准备一条要发布到 PowPow 的泡泡/草稿) and immediately marks the scope limit that defines it: saved as draft, not public. It explicitly contrasts with the sibling publish_post, so an agent distinguishes the two without opening either schema.

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?

Gives the exact when-to-use/when-not rule: this tool only creates the draft, and真正公开必须再调用 publish_post 并带上返回的 draft_id. The alternative tool and the condition that selects it are both named, leaving nothing to inference.

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