apply_geometric_texture

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

With no annotations, the description carries the full burden, and it does disclose some real behavior: a 3D stage panel opens on success, oversized meshes are auto-decimated, and a monthly quota applies. It omits what an agent most needs for a 29-param mutation – where the textured mesh is written, whether the operation is destructive to the input, and any auth/tier gating beyond the quota count.

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 first sentence is well front-loaded, but the paragraph after the pricing block restates the inline 3D stage almost verbatim from the opening sentence, and the upgrade URL plus 'the PNG preview is the floor, not the whole experience' is marketing copy rather than operational guidance. Roughly half the text is redundant or promotional.

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 29-parameter, annotation-free, output-schema-free tool, the description should explain the texture/face/region/depth surface and where the result lands. Instead it spends its length on the viewer and tier limits, leaving an agent unable to construct a correct call or predict the returned artifact.

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 55% across 29 parameters, and the description explains none of them – not face, region, surface, texture, depth_mm, projection, or the mark_* family. Several params carry no schema description at all (input_path, face, region, surface, texture, depth_mm, resolution), so the description leaves large gaps unaddressed.

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 opening sentence gives a specific verb and resource – 'Apply a procedural texture as physical surface relief' – which tells an agent this displaces geometry rather than painting color. However it never names the close siblings it competes with (apply_procedural_texture, apply_image_texture, decorate_surface), so differentiation must be inferred from the name alone.

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?

There is no statement of when to choose this over apply_procedural_texture or apply_image_texture, nor any prerequisites such as what input_path must point to or whether a printer_id is needed. The only conditional content is a quota note (3 textures/month on free tier), which is useful but is billing, not usage guidance.

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