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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, and the description adds nothing beyond that profile. 'RETURNS: 结果段落' merely restates the tool name rather than describing output shape, length, or language behavior, and it never explains what non-read-only behavior actually occurs or what happens when the params payload is empty.

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?

The keyword-block formatting (title, USE WHEN, ALIASES, RETURNS) makes the trigger condition easy to scan, but the title is repeated verbatim at the start and 'RETURNS: 结果段落' duplicates the tool name without information. The ALIASES list is bulk that does not help an agent decide or call.

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 five parameters, a nested payload object and no output schema, the definition covers purpose and trigger but leaves the return content undefined ('结果段落' only), so an agent cannot anticipate the paragraph's structure or language. The parameter side is fully carried by the schema, so the remaining gap is moderate rather than severe.

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%: lang, model_type, design_type and polish_level all carry inline explanations with enumerated values, and the nested params payload is documented as the statistical result carrier. The description adds no parameter meaning beyond the schema, so the baseline 3 applies.

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 gives a specific verb+resource ('wants them written into a results paragraph') and the USE WHEN clause anchors it to statistical results as input, which does separate it from prose-oriented siblings like academic_polish. However, it never explicitly contrasts itself with section_writer, the closest sibling, so an agent must infer the boundary.

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 has statistical results and wants them written into a results paragraph' clause states the triggering condition clearly and concretely. It gives no when-not-to-use conditions or named alternatives, which keeps it below a 5.

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