adapt_asset_materials

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: Preview creates separate material/asset variants and real before/after renders; Apply preserves geometry/textures and refuses changed assignments; unsupported-field warnings are surfaced. It omits auth/permission requirements and reversibility guarantees, but the behavioral disclosure is unusually rich.

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?

Front-loads the purpose, then layers mode-specific behavior in short clauses. Dense semicolon-heavy phrasing and a slightly scattered ordering cost it, but every sentence carries information and nothing is padding.

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 complex 6-param, zero-annotation, no-output-schema tool, the description covers behavior well but not the full contract. Missing explanations for plan_id and paths, and no indication of mode values or what a plan/selected-row lifecycle looks like, leave an agent guessing on invocation.

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 coverage is 0%, so the description must compensate. It maps some params meaningfully ('fields: color, roughness, texture_scale' to fields, 'reference can be a native material or model' to reference, 'selected row IDs' to selected, 'mode' implied by Preview/Apply), but leaves paths and plan_id completely unexplained — a real gap for a 6-param tool.

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 specific verbs (preview, apply/undo) against specific resources (material slots on Unity prefabs or UE static meshes), and clarifies the reference input can be a native material or model. An agent can tell this apart from siblings like create_variants or match_game_style without opening the schema.

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 distinguishes its two modes clearly, saying what Preview does vs what Apply does, and adds a caution ('do not claim visual equality across different shaders'). It does not name sibling alternatives or prerequisites for choosing this over create_variants/set_scene_look, so it stops short of explicit routing.

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