更新运营草稿

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

The description goes well beyond the annotations (readOnlyHint=false, destructiveHint=false), disclosing that material files are re-read, contentHash is recomputed, approval is cleared and state reverts to draft on hash change, and that Xiaohongshu is never accessed. These are exactly the side effects an agent must predict before calling a mutating tool, with no contradiction against the annotation flags.

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?

Five short sentences, each carrying distinct information: the action, the partial-update rule, side effects, an immutability constraint, and a system boundary. The main action is front-loaded and there is no filler.

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?

Lifecycle constraints, side effects, partial-update behavior, and the closed-world boundary are all covered, which is strong for a mutating tool. The main gap: with no output schema present, the description never states what the tool returns or what failure modes exist (e.g., validation errors or unknown draftId).

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 the critical partial-update semantics ('省略的字段保持原值') that governs every optional parameter, and explains that assetPaths drive contentHash recomputation. However, the meanings of campaign and topics still rely on inference from their names, with no per-parameter guidance.

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 — '更新本地草稿字段' (update local draft fields) — reinforced by the title '更新运营草稿'. The partial-update and hash-recomputation details distinguish it from lifecycle siblings like submit_for_review, approve_draft, and cancel_draft.

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?

Clear context is given: omitted fields retain their values (partial update), and an explicit exclusion is stated — published or canceled drafts cannot be modified. However, no sibling is named as an alternative (e.g., when save_draft should be used instead), so the when-not condition exists but alternative routing is left implicit.

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