scene_change_plan

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

The description lists five concrete behavioral steps, including 'Take checkpoint' and 'Return plan_id + baseline status', adding context beyond the minimal readOnlyHint:false annotation. It does not disclose failure behavior or whether dry_run suppresses side effects, but the core workflow is transparent.

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 concise, well-structured with a numbered list, and front-loaded with the essential purpose. Every sentence/step adds value, and there is no redundant filler.

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?

The workflow and high-level return values (plan_id, baseline status) are described, but important gaps remain: the exact return structure, the effect of dry_run, the format of targets, and whether any actual scene mutation occurs. Without an output schema, these omissions are noticeable but not fatal for a planning tool.

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%, and the description does not explain the meanings or usage of goal, dry_run, or targets. The step 'Resolve targets via resolve_scene_refs' vaguely references target handling but does not map to the targets parameter, leaving all parameters semantically unexplained.

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 this is a pre-flight planning tool for safe scene edits with concrete steps: compile check, console check, target resolution, checkpoint, and returning a plan_id. This distinguishes it from siblings like apply_scene_change and lint/validate tools.

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 word 'Pre-flight' strongly implies this should be used before making scene edits, and the numbered steps give a clear context. However, it does not explicitly name alternatives or state when not to use this tool, so the guidance is clear but not fully explicit.

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