new_scene

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

With no annotations provided, the description carries full burden. It discloses the destructive nature (resetting to empty scene), the suppress_save_prompt=True behavior, the default-disabled permission gate, and the side effect of invalidating caches. This is exceptionally transparent.

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 description is concise, with the main action stated in one sentence, followed by a bilingual safety warning and a side-effect note. It is front-loaded and each sentence adds value, though the bilingual repetition slightly lengthens it.

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 destructive reset tool with no annotations and no output schema, the description covers the core function, safety gate, and side effects. It is complete enough for an agent to decide and invoke correctly. Return value is not described, but for a reset action this is acceptable.

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 tool has zero parameters, and the input schema is empty (100% coverage trivially). The description adds context about suppress_save_prompt and cache invalidation, which are not parameters but internal behaviors. No parameter explanation needed, so baseline 4 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 clearly states 'Reset Houdini to an empty scene', which is a specific verb+resource. It does not explicitly distinguish from siblings like load_scene or save_scene, but the meaning is unambiguous and unique enough.

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 description provides explicit when-to-use guidance via the environment variable gate: it is disabled by default and only works when HOUDINI_MCP_ALLOW_NEW_SCENE=1 is set. It also explicitly warns against autonomous use ('禁止 AI 自主清空用户场景'), giving a clear exclusion. No alternatives are mentioned, but the safety constraint guides usage effectively.

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