unreal_mesh_preview

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is set. The description adds substantial behavioral context: requires explicit material policy, uses centimeter offsets and label prefix/suffix, accepts only exact native StaticMeshActors, refuses custom components/attachments/physics, limits to one bounded copy per source, and clarifies it never clones arbitrary actor state. This goes well beyond what annotations provide.

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 dense yet properly front-loaded: purpose first, then requirements, constraints, and workflow. Every sentence adds necessary constraints or steps; no filler. The paragraph structure is logical and the length is justified by the two recipe variants and the explicit refusal conditions.

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 tool with two recipe types, multiple constraints, and a follow-up workflow, the description covers all critical aspects: what it targets, what it refuses, required parameters, and how to proceed after the preview. It even points the agent to result.preview.plan_id and verification_checks, so an agent can call it correctly without additional documentation. Output schema exists, so not describing return values in detail is acceptable.

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%, so the description carries the full burden for explaining the recipe parameter. It clarifies the two recipe kinds (replace and duplicate), their required policies, offsets, label behavior, and actor constraints. Although it doesn't enumerate every schema field, it conveys the practical meaning and requirements for the discriminator and key properties, which is sufficient for correct invocation.

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 first sentence states a specific action and resource: 'Inspect and preview mesh replacements or one bounded native mesh copy per source.' This clearly distinguishes it from generic preview tools like unreal_preview by restricting to mesh replacements/copies of native StaticMeshActors, and the rest of the description reinforces that scope.

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?

Provides clear usage context: material policy requirements for replace, offset/label behavior for duplicate, and explicit refusals for non-native actors. It also outlines a follow-up workflow (review plan_id, apply separately, run verification_checks with unreal_verify). It does not explicitly name alternative tools for other cases, so it misses the full 'when-not-to-use' contrast, but the constraints strongly imply when this tool is appropriate.

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