Scene

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

The annotations already mark the tool as destructive. The description adds specific behavioral context for save_copy (e.g., 'writes current dirty state to path as backup; active scene reference unchanged') and clarifies include_unsaved is always True. However, it does not explain side effects for destructive actions like discard or close beyond what the annotation states.

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 compact yet organized, listing actions as a shorthand and then explaining parameter requirements in a structured way. It efficiently packs essential details without unnecessary elaboration, though it reads as a dense run-on in places.

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 nine actions and overlaps with siblings like `set_active` and `scene_change_plan`, the description could be more complete. It covers parameter mapping well but does not describe return values for actions like `list`, nor does it explain when to use the scene tool vs. its siblings. The absence of an output schema increases the need for these details.

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 description adds meaningful parameter semantics that go beyond the schema. It explicitly ties each action to required parameters ('path required for open/save/open_additive/close/set_active/save_copy'), clarifies the 'scene' parameter for identifying multiple loaded scenes, and explains the `include_unsaved` behavior (always True for save_copy). This compensates for the 75% schema coverage.

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 'Scene management' and enumerates nine specific actions (new, open, save, discard, open_additive, close, set_active, list, save_copy), making it easy to understand the tool's scope. It is less explicit in differentiating from the sibling `set_active` tool, which also handles scene activation, so it loses a point on full distinction.

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 per-action parameter requirements (e.g., 'path: required for open/save/open_additive/close/set_active/save_copy'), but it does not explain when to use this tool versus alternatives like `scene_change_plan` or `apply_scene_change`. There is no mention of exclusions, warnings, or alternative tool guidance.

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