生成可重放的当前场景序列化快照

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the agent knows this is a safe read operation. The description adds the concept of 'replayable' (可重放) and 'serialized snapshot' (序列化快照), which implies the output is a serialized representation that can be used to replay the scene state. However, it does not disclose what exactly is captured, whether the snapshot is stored or returned, or any side effects. With annotations covering the safety profile, a 3 is appropriate – the description adds some behavioral context but not rich detail.

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 a single sentence, which is concise and front-loaded with the core action. However, it is also a near-verbatim repetition of the title, adding little new information. It earns its place as a minimal statement but does not use the available space to add differentiating or clarifying details. It is not bloated, but it is under-specified.

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?

Given the tool has 6 parameters, no output schema, and no parameter descriptions, the description is incomplete. It does not explain what the snapshot contains, how it is returned, whether it is stored, or how 'replayable' works. The sibling tools suggest a rich scene-management context, and this tool's description does not provide enough context for an agent to know what to expect from the call or how to interpret the result. The annotations cover safety, but the operational context is missing.

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 0%, and the description does not explain any parameters. The schema shows required projectId and params, with params being an empty object, but the description does not clarify what projectId refers to or what params should contain. Since the schema provides no descriptions and the description text adds no parameter meaning, the agent has to guess. The empty params object is particularly confusing – it suggests no parameters are needed, but the schema requires it. The description should at least explain that params is an empty placeholder or what projectId identifies.

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?

Tautological: description restates name/title.

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 no guidance on when to use this tool versus alternatives. It does not mention that this is a read-only snapshot operation, nor does it explain when one would prefer it over cocos_scene_query, cocos_scene_diff, or cocos_runtime_capture. The agent is left to infer usage from the name and description alone, with no explicit context or exclusions.

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