blender_scene_ops

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

Annotation Contradiction: annotations set destructiveHint to false, but the description includes 'purge orphans,' which is inherently a destructive operation that deletes unused datablocks. This directly conflicts with the safety signal the annotation sends. The description also gives no detail about side effects of apply_instances or whether actions are irreversible.

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 a single compact sentence that front-loads the tool's category and then enumerates its operations with no filler. Every phrase earns its place, and the list aligns naturally with the action enum.

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?

With seven distinct actions, six parameters, no output schema, and annotations that are all false, the description is not complete enough. It fails to specify which parameters apply to which actions, what each action returns, and whether destructive actions like purge_orphans require confirmation or have undo implications.

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 100%, so the baseline is 3; every parameter has a description. The tool description adds some semantic context by mapping actions to concepts like 'duplicate a parent with all children' and 'instance or realise collections,' but it does not clarify action-specific parameter requirements or coordinate/unit semantics beyond the schema.

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 names a concrete category ('Hierarchy and housekeeping') and enumerates specific operations: duplicating a parent with children, instancing/realising collections, purging orphans, and inspecting depsgraph/add-ons/datablock counts. This clearly differentiates it from sibling tools like blender_duplicate_objects or blender_list_objects by focusing on hierarchy-level and scene-housekeeping operations.

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 implies when to use the tool through its list of hierarchy and housekeeping operations, and the action enum maps those operations precisely. However, it never explicitly distinguishes this tool from alternatives such as blender_duplicate_objects, blender_create_collection, or blender_delete_objects, nor does it state when another sibling would be preferred.

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