production.material_build_shader

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

Annotations already declare this is not read-only, not destructive, and not idempotent, so the description usefully adds the default inspect/propose behavior and the scoped write condition for owned candidate materials. It also reassures that original slots, images, UVs, geometry, and animation remain unchanged, which is meaningful behavioral context beyond annotations.

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 front-loaded with the tool name and the critical default/apply distinction, and it avoids wasteful repetition. It is dense and jargon-heavy in the second sentence, but appropriately sized for a complex production tool.

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?

The presence of an output schema reduces the need to explain return values, and annotations plus description cover the safety profile and apply semantics reasonably well. Still, with 8 optional parameters at 0% schema description coverage, the omission of parameter meanings leaves the definition incomplete for safe 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 description coverage is 0% across 8 optional parameters, so the description must carry parameter meaning. It only clarifies apply=true and alludes indirectly to profiles and material plan references, leaving material, definition, options, object_name, operation_id, and material_name essentially undocumented.

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 description states a specific mode-based purpose: inspect or propose by default, with apply=true writing only owned candidate materials. It distinguishes the default vs mutation behavior clearly, though it does not explicitly contrast this tool with nearby siblings such as material_create_pbr or material_create_candidate.

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?

It gives a clear default mode and the condition for writing (apply=true on owned candidates), plus workflow expectations around material plan references, QA, lighting, and review. However, it does not name alternative tools or state when not to use this in favor of a sibling.

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