blender_ai_mesh_cleanup

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

With no annotations provided, the description bears the full burden of behavioral disclosure. It does disclose the mutating nature and enumerates the concrete effects (removing geometry, merging vertices, recalculating normals), which is genuinely transparent about the operations an agent should expect. It stops short of warning that these removals are destructive and irreversible — no mention of in-place modification or whether the object can be restored — which matters for a tool that deletes geometry.

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?

Two sentences with zero filler: the first front-loads the verb and resource and enumerates the operations; the second supplies the pipeline context. Every clause earns its place, and the structure is immediately scannable.

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 mutating tool with no annotations and no output schema, the description covers the core purpose and pipeline position, and the schema fully documents all six parameters. It omits a few useful details — behavior when object_name doesn't exist or isn't a mesh, reversibility, and how status/results are reported — but these are moderate gaps for a cleanup whose operations are largely self-explanatory.

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%: every parameter already carries a clear description with its default value, so the baseline of 3 applies. The description adds only mild reinforcement by listing operations (remove doubles, fix normals, remove loose geometry, remove degenerate faces) that map to the boolean parameters, but it contributes nothing new about merge_distance's units or edge-case behavior.

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 opens with a specific verb and resource ('Clean up a generated mesh') and enumerates the exact operations performed (remove doubles, fix normals, remove loose geometry, remove degenerate faces), which map directly to the tool's boolean parameters. It also anchors the tool in a pipeline stage ('post-processing step after AI model generation'), which separates it from generic mesh-editing siblings. It loses the top score because the near-duplicate sibling blender_ai_fix_mesh_issues is never explicitly differentiated.

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 explicitly positions the tool as the 'essential post-processing step after AI model generation,' giving the agent a clear, concrete signal for when in a workflow to invoke it. However, it never names alternatives or states when NOT to use it; with close siblings like blender_ai_fix_mesh_issues and blender_ai_mesh_optimize present, the lack of exclusion guidance prevents a 5.

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