hold_scene

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

Annotations already declare readOnlyHint=true and destructiveHint=false; the description adds that fetch_scene '完整还原' / 'restores it exactly' and frames the tool as a pre-risk checkpoint. It does not mention that a new Hold may overwrite the previous held state, but the provided behavioral context is solid for an annotated snapshot tool.

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 definition is short and front-loaded, starting with purpose, then usage, then restore behavior. The English section is a direct duplication of the Chinese content, adding no new information but not making the description unreasonably long.

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 zero-parameter, no-output-schema action, it covers the essential lifecycle: when to call it, what it captures, and which sibling restores it. The main gap is not disclosing single-slot/overwrite semantics of a Hold, but nothing essential for a first call 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?

The tool accepts zero parameters, so there are no parameter semantics for the description to clarify. With an empty schema and 100% schema description coverage, the baseline applies and the description correctly stays silent.

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 opens with '保存当前场景状态' ('Save the current scene state') and anchors it to Max's Hold, making the verb and resource explicit. The pairing with fetch_scene clearly distinguishes this restore-point tool from file-save siblings like scene_save.

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?

It explicitly says '在危险操作前使用' / 'Use it before risky operations', giving a clear trigger for when to call the tool. It does not spell out exclusions or compare with alternatives like undo_last, so it stops short of full when/when-not guidance.

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