blender_generate_pbr_set

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

Annotations only state readOnlyHint=false, idempotentHint=false, and destructiveHint=false. The description adds meaningful behavioral context: BaseColor is written sRGB while data maps are Non-Color, all maps come from one shared height field and seed, and passing `material` adds an AO multiply onto Base Color. It does not disclose file-output side effects or return behavior, but it goes well beyond the 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 three concise sentences with no filler. The first sentence states the core purpose, the second explains the generation consistency and color-space behavior, and the third gives the material-wiring option. Useful information is front-loaded and every sentence earns its place.

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 16-parameter tool with low schema coverage and no output schema, the description leaves important gaps. It never explicitly states that files are written to output_dir, what the response contains, or how the procedural parameters interact with the shared height field. It is sufficient for a default or simple invocation, but not for informed custom use.

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 only 38%, leaving most of the 16 parameters undocumented. The description adds some meaning for `seed` (all maps derive from one seed) and `material` (wires maps into a Principled BSDF with AO multiply), but it does not compensate for the many procedural parameters an agent would need to tune, such as scale, octaves, pattern, contrast, roughness range, metallic, or normal_strength.

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 starts with the specific verb 'Generate' and names five concrete map types: BaseColor, Roughness, Metallic, Normal, and AO. It further distinguishes the tool by explaining that all five maps derive from one height field and one seed, making them read as a single material. This clearly separates it from texture-generation siblings like blender_generate_texture or blender_bake_texture.

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 clearly frames when to use the tool: when a matched PBR set is needed, and it gives conditional guidance for the `material` parameter ('Pass material to connect everything...'). It does not explicitly name alternatives or state when not to use this tool, which keeps it one step below a perfect score.

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