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

The RETURNS line ('润色后文本') adds real value by telling the agent the output is polished text rather than an edit history, which annotations do not convey. However, nothing clarifies whether the source content is persisted or modified, which matters given readOnlyHint=false on what is essentially a transform, and nothing about length/format changes to expect.

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?

A single pipe-delimited block with front-loaded title, then USE WHEN, ALIASES, RETURNS in priority order. Every segment serves routing or output expectation; there is no filler prose.

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 three-parameter, single-purpose transform tool with fully documented params and a stated return payload, the definition covers what an agent needs to select and call it. The only real gap is the absence of any mention of the polishing-level control, which a caller may need to set deliberately rather than by default.

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 schema already documents lang, level (including enum values and legacy aliases), and content, so the baseline is 3. The description itself adds no parameter meaning at all — notably it never mentions the conservative/standard/enhanced/top_journal level choice, which is the tool's main user-facing control.

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+resource ('academic language polishing') and immediately narrows scope with concrete sub-goals: academic English, remove Chinglish, tighten wording. An agent can tell this apart from siblings like citation_format or deep_peer_review without opening a 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?

The 'USE WHEN: the user wants a paragraph polished' clause gives a clear triggering condition, and the ALIASES list (润色, 改英语, 中式表达, polish, proofread) materially helps routing on Chinese and English phrasings. It stops short of 5 because no when-not condition or named alternative is given, e.g. what to use for whole-manuscript editing.

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