打开已有场景；有未保存修改时拒绝切换

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

Annotations already declare destructiveHint=true, so the agent knows this operation can be destructive. The description adds the specific guardrail behavior: it refuses to switch when there are unsaved changes, which is valuable context beyond the annotation. However, it doesn't disclose what happens on refusal (error? no-op?), whether the current scene is closed, or any side effects on the editor state. With annotations covering the destructive nature, the description adds some but not rich behavioral context.

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 concise sentence that front-loads the primary action and includes the key behavioral constraint. Every word earns its place, and there is no fluff. It is appropriately sized for the information it conveys, though it could be slightly more structured with separate sentences for action and behavior.

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?

This is a mutation tool (destructiveHint=true) with 6 parameters, 0% schema description coverage, and no output schema. The description is too thin to fully support correct invocation: it doesn't explain the uuid parameter, the meaning of projectId, the refusal behavior's error handling, or what happens after a successful open. An agent would need to infer too much about how to call this tool correctly.

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%, so the description must compensate for the 6 parameters. The description mentions 'scene' and 'unsaved changes' but doesn't explain that the 'uuid' parameter identifies the scene to open, nor what projectId, instanceId, operationId, expectedRevision, or runtimeInstanceId mean. The nested params object with a required uuid is left entirely undocumented. The description adds almost no parameter-level meaning.

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 implies when to use this tool: when you want to open an existing scene, and it warns that it will refuse if there are unsaved changes. This gives some context about a precondition (no unsaved changes) but doesn't explicitly state when to use alternatives like cocos_scene_query or cocos_scene_snapshot, nor does it mention any workflow prerequisites like needing a projectId or instanceId.

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