production.material_inspect

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

The description does disclose valuable behavior: writes happen only with apply=true, only owned candidate materials are touched, and original slots, images, UVs, geometry and animation are preserved. But this directly conflicts with the annotation readOnlyHint=true, so an agent that trusts the safety hint would be wrong about the tool's write capability; the contradiction caps the score despite the otherwise informative disclosure. It also never describes the 'propose' output or whether proposals are persisted.

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?

Three tight sentences with the default behavior and the apply gate front-loaded, followed by the no-mutation invariant. Some clauses are internal jargon ('material plan references', 'explicit channels/profiles') that cost more parsing than they return.

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?

An output schema is present so return shape need not be described, and the immutability guarantee is a useful addition. Still, for a 7-parameter material tool the description omits what is actually inspected, what a proposal contains, and how the undefined 'definition'/'options' objects drive the result.

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% across 7 parameters, so the description carries the full burden. It explains only apply (the critical write gate) and gestures at 'channels/profiles', leaving options, material, definition, object_name and material_name with no meaning at all — including whether 'material' and 'material_name' are alternatives.

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 a concrete verb and resource ('material_inspect: inspect or propose') and clarifies the default mode versus the write mode gated on apply=true. It does not distinguish the tool from near-neighbours such as material_status, material_analyze_nodes or material_quality_report, and 'propose' is never defined.

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?

Gives real workflow context: run inspection/proposal first, then route lifecycle calls through material plan references and do technical QA, controlled lighting and a visual review before acceptance. It stops short of naming the specific sibling tools (e.g. material_validate_pbr, material_render_multilighting, material_accept) or stating exclusions.

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