scene

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the agent is aware of the destructive nature. The description adds some behavioral context such as 'scene: save/discard target when multiple scenes loaded', but it does not elaborate on the consequences of destructive actions like 'discard' or 'close' beyond their names. No contradiction with annotations.

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 tight and front-loaded: it starts with 'Scene management' and immediately follows with action and parameter rules. Every sentence provides necessary information with minimal verbosity, making it efficient for an agent to parse.

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 multi-action nature and no output schema, the description covers action semantics and parameter requirements well. However, it does not describe return behavior for any action (e.g., what 'list' returns), nor does it explain side effects (beyond what action names imply). This is a minor gap, but overall the description is sufficient for selecting and invoking the 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?

With schema_description_coverage at 0%, the description fully compensates by explaining that 'action' accepts specific values (new|open|save|discard|open_additive|close|set_active|list), 'path' is required for specific actions, and 'scene' targets save/discard when multiple scenes are loaded. This adds substantial meaning beyond the schema's bare property definitions.

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 states the resource (scenes) and provides a clear list of actions (new|open|save|discard|open_additive|close|set_active|list), making the tool's purpose very specific. It distinguishes itself from sibling tools like search_scene by enumerating a broad management scope rather than just searching.

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 gives clear context on when to use the tool via its action list and parameter conditions (e.g., 'path: required for open/save/open_additive/close/set_active'), but it does not explicitly compare against sibling tools or state exclusions. There is no mention of when to use 'search_scene' instead of this tool's 'list' action, but the action list itself implies usage.

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