production.material_review

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

Annotations already state destructiveHint=false and readOnlyHint=false, and the description usefully confirms the scope of writes ('apply=true writes only owned candidate materials') and explicitly lists what is untouched: slots, images, UVs, geometry and animation. That is real behavioral context beyond the annotations, though idempotency (idempotentHint=false) and what a proposal run actually produces are not discussed.

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, no repetition, and the highest-value fact (propose by default, apply writes) is front-loaded. The remaining clauses about QA, lighting and unchanged data are dense but each adds a distinct constraint.

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?

It covers the mutation safety profile and the non-destructive guarantee, which matters for a tool with destructiveHint=false but readOnlyHint=false, and an output schema exists so return values need no explanation. Still, with 8 totally undocumented parameters and an unexplained 'options'/'definition' object pair, an agent lacks enough to call it correctly in anything but the simplest case.

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% across 8 parameters, so the description carries the full burden and it explains only 'apply'. Options, profile, material, material_name, definition, object_name and operation_id get no meaning at all, leaving most of the call surface undocumented in both schema and description.

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?

It names the mode split ('inspect or propose by default; apply=true writes only owned candidate materials'), which is useful, but 'material_review' as a resource is never concretely defined and it never distinguishes itself from close siblings such as material_inspect, material_accept or material_apply_candidate. An agent can tell it is about materials and that it has a proposal mode, but not precisely what it returns or how it differs from the inspect/accept tools.

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 default-vs-apply distinction plus 'a real visual review before acceptance' implies a pre-acceptance review step, which is genuinely useful usage context. However 'use material plan references for lifecycle calls' is cryptic, and no alternative sibling (material_inspect, material_accept, material_reject) is named with an explicit when-to-use condition.

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