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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so '不改变输入' merely repeats structured data and earns no credit. What the description does add is the scope of the check (inventory, contacts, track connections, orientation) and that findings are returned as concrete issues, but it says nothing about output format, error reporting, or failure modes.

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 compact sentence: input first, then what is checked, then what is returned, then the non-mutation guarantee. Zero filler and well front-loaded.

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 read-only validator with no output schema, the description covers input, checked dimensions, result shape in outline, and side-effect behavior. The only gap is what '具体问题' actually looks like, but that is minor for a review tool whose annotations already establish safety.

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 50%, and the bare 'document' object carries no schema description, so '传入完整文档' usefully clarifies that a full document (not a partial one) is expected and that 'intent' is optional. Still, the description adds no detail on intent sub-fields beyond what the intent schema already documents, 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 names a specific verb (核对/检查) and enumerates the resources checked: 组件清单、接触、轨道连接和方向, plus the return (具体问题). It is clearly distinguishable from build_scene/export_scene, but it does not differentiate itself from the closest sibling, inspect_scene, so an agent still has to infer which inspection tool applies.

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?

Passing the '完整文档' implies you should call this once you have a full scene document, and '可选几何意图' signals intent is optional. However, there is no explicit when-to-use or when-not-to-use guidance, and no sibling (e.g. inspect_scene, analyze_motion) is named as an alternative.

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