remove_geometry_collection_source

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered. The description adds genuinely useful non-schema behavior: the removal is shallow (entry only, no re-fracture), and the presence of an 'already_absent' return field signals what happens when the target is not present. It does not mention save/persistence behavior or permissions, keeping it at a 4. The idempotentHint=false annotation combined with 'already_absent' is a mild tension but not a contradiction.

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 core behavior and non-effect warning are front-loaded in one clear sentence, with the return shape appended. The returns block is somewhat verbose, but it is the only place return values are documented (no output schema), so it earns its space.

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 no output schema, the description usefully enumerates the return fields including 'removed', 'already_absent', and 'saved', which is important for a destructive mutation. It does not clarify the schema's implicit requirement that exactly one of index/source_mesh_path be supplied for a required-only geometry_collection_path signature, nor whether the asset is saved to disk, leaving a small gap.

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%, and the schema already explains the index / source_mesh_path exclusivity and the geometry_collection_path format, so the baseline is 3. The description's 'StaticMesh source reference' wording loosely maps to source_mesh_path and removed_index hints at the index parameter, but it adds no new syntax or constraint detail.

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?

States a specific verb+resource ('Remove a StaticMesh source reference from an existing geometry collection') and explicitly names the sibling it inverts, add_geometry_collection_source. The added scoping clause ('drops the GeometrySource entry only, does NOT re-fracture the core geometry') distinguishes it from the fracture/cluster siblings in the same family.

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?

Names the inverse operation and the precise scope of what is affected, which gives an agent clear context for when this is the right call versus fracture_geometry_collection or add_geometry_collection_source. It stops short of stating prerequisites (e.g. that the collection must exist / be loaded) or exclusions, so it falls just below the explicit when/when-not bar.

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