Validate a draft before saving

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

Annotations (readOnlyHint, idempotentHint, destructiveHint) already indicate a safe read operation, but the description adds critical behavioral context: it is local-only, does not access the network, and returns errors/warnings/summaries. It also specifies exactly what validation is performed, going beyond the structured annotations.

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 concise, front-loaded sentences. The first sentence states purpose and scope, the second details checks, the third covers output and network behavior. Every sentence earns its place with no fluff.

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 validation tool with two parameters (one being a rich array), the description covers the key aspects: what is validated, that it is local-only, and what it returns. It does not detail the return format, but the response_format parameter handles that. The absence of an output schema makes the description's mention of 'errors, warnings, and per-article summaries' essential and sufficient for an agent to understand the tool's behavior.

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 description explains which fields are validated (title, author, digest, content_html, cover_media_id), adding meaning beyond the schema. However, it does not mention the response_format parameter or cover boolean fields like show_cover/open_comment, which the schema does describe. With 50% schema coverage, the description partially compensates but could go further.

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 uses a specific verb (validate), names the resource (article drafts), and lists concrete actions (checks lengths, forbidden tags/URLs, cover media IDs). It clearly distinguishes itself from sibling tools like create_draft or read_article by focusing on validation rather than mutation or retrieval.

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 title 'Validate a draft before saving' and description 'Local-only validation' clearly imply use before saving a draft, especially compared to wechat_official_create_draft. No explicit 'use this when' or 'instead of X' is stated, but the context is strong enough for an agent to infer the intended scenario.

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