production.material_validate_graph

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

The description does disclose the write surface ("apply=true writes only owned candidate materials") and enumerates what is left untouched (slots, images, UVs, geometry, animation), which is genuinely useful. But this write capability directly conflicts with the declared readOnlyHint=true, so an agent reading both signals cannot be sure whether the call can mutate the scene. The contradiction undercuts the transparency the prose otherwise provides.

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?

It is short (about 45 words) and front-loads the default-versus-apply distinction, with no filler sentences. But the second sentence is a dense, comma-spliced list of unrelated prerequisites ("plan references... explicit channels/profiles, technical QA, controlled lighting and a real visual review") that is hard to parse and repeats the tool name as a prefix.

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 exists, so return values need no explanation, but for a 7-parameter tool with zero schema coverage the description leaves most inputs undefined and its mode semantics conflict with the annotations. An agent would not know how to construct a valid proposal call without opening the schema and guessing.

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 7 parameters, so the description must carry the burden. It explains only 'apply' and gestures at 'profile' via "explicit channels/profiles"; it says nothing about options, material, definition, object_name or material_name, nor about the relationship between material and material_name. Most parameters remain opaque.

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 name plus the phrase "material_validate_graph" signal validation of a material graph, and "inspect or propose by default; apply=true writes" clarifies the two modes. However, the description never states what is validated in the graph (node wiring, channels, profile conformance) and does not distinguish it from the many sibling validators such as material_validate_pbr, material_validate_normals or material_validate_profile. Purpose is inferable but not crisply stated.

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?

"inspect or propose by default; apply=true writes" gives an implicit default-mode rule, and the second sentence lists workflow prerequisites (plan references, explicit channels/profiles, technical QA, controlled lighting, visual review before acceptance). But it never says when to pick this tool over the sibling material_validate_* tools or when to stop at propose versus apply. Guidance is implied rather than explicit.

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