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

Annotations already declare this is read-only, idempotent, non-destructive and not open-world; the description adds genuine value on top by disclosing that it emits a prompt plus upload/material steps and delegates generation to the harness's own image tool. That clarifies the call has no side effects and no compute cost, though it does not describe the shape of the returned prompt/steps.

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, no filler. The scope statement comes first, the return/delegation behavior next, and the negative constraint ('does not generate... or spend Blender compute') last, which is the right ordering for an agent deciding whether to call.

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 19-param planning tool with no output schema, the description summarizes the return ('a prompt and upload/material steps') but does not describe its structure, and it leaves most parameters undocumented while coverage is low. It is adequate to understand the tool's role but thin for calling it precisely.

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 32% across 19 parameters, so the description carries much of the documentation burden, yet it mentions no parameter at all. The artifact-type list echoes the purpose enum but adds no syntax, format, defaults or interaction guidance (e.g. how layout, resolution and physicalCoverageMeters relate).

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 specific verb and resource ('Plan a source image') and enumerates the artifact types it covers (surfaces, decals, trim sheets, atlases, environments, animation). It also carves out a clear boundary against the generation siblings: it returns a prompt and steps, not pixels, and does not 'spend Blender compute.'

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 gives a usable selection condition: use this when you want a prompt plus upload/material steps rather than an actual generated image or spend. It does not, however, name the concrete alternatives (e.g. texture_maps_create, material_from_image, asset_generate_3d) that a caller would be choosing between.

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