Scene Rollback

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

Annotations only cover the safety profile; the description supplies the failure model (aborts if the auto_before_rollback export fails), the escape hatch and its reported result value (safety_snapshot="skipped_by_user"), the null scene_rebound_to case, and the loss of undo history. That is exactly the beyond-annotations context this dimension rewards.

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?

Purpose is front-loaded in sentence one, then behavior, failure mode, and follow-up in a tight four-sentence block with no filler. The S1/S2 labels are unexplained internal jargon that costs a little clarity for no gain.

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 state-mutating tool with full schema coverage and an output schema, the description covers everything an agent still needs: failure/abort behavior, the escape hatch, edge-case scene states, and the required follow-up call. Nothing material 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 coverage is 100%, so baseline is 3, but the description genuinely deepens discard_current_state ('pass ... to escape', with the resulting safety_snapshot value) and explains the untitled-scene implication for filename/rebinding. It stops short of adding format detail for session_key.

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 first sentence states a specific compound action (open a checkpoint and rebind the scene) with a resource, which is immediately distinguishable from siblings like scene_checkpoint (creates) and scene_snapshot (captures). The two-outcome behavior (S2 vs S1) further pins down what the call does in the normal case versus untitled scenes.

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 gives concrete conditions: pass discard_current_state=True when the safety snapshot fails, and call scene_snapshot afterwards to rebuild undo context. Edge cases (untitled scenes, ad-hoc snapshots) are called out explicitly. It lacks an explicit statement of when to prefer this over scene_checkpoint/scene_snapshot beyond the follow-up pointer, so it falls just short of 5.

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