blender_fix_topology

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

The annotations declare destructiveHint=false, but the description explicitly says the tool will 'delete loose geometry', which is a destructive modification. This is an annotation contradiction, and the description provides no safety caveats or side-effect disclosure beyond that.

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 front-loaded sentence that states the purpose, lists the concrete operations, and notes the output reporting. There is no filler or repeated information from the schema.

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 description covers the core operations and the before/after reporting, and the schema covers the selection default. However, it omits prerequisites, when to run the repair, and important safety context, especially given the deletion behavior and the absence of an output schema.

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 60%, and the description helps map weld_distance to merging, recalc_normals to recalculating, and remove_loose to deleting loose geometry. However, it adds nothing meaningful about the 'objects' parameter or response_format, and does not specify units or thresholds for weld_distance.

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 the action ('repair'), the target resource ('mesh problems'), and the specific operations (merge duplicate vertices, recalculate normals, delete loose geometry), plus the reporting behavior. This distinguishes it from sibling tools like blender_fix_uv_mapping or blender_auto_validate.

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: when a mesh has duplicate vertices, bad normals, or loose geometry. However, it gives no explicit guidance on when not to use it, no prerequisites, and no mention of alternative sibling tools, which is needed given the large set of Blender repair/validation tools.

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