Add cubes

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

Annotations already state it mutates (readOnlyHint=false), is non-idempotent and non-destructive, so the safety profile is covered. The description adds a genuinely useful behavioural fact beyond that: creation is atomic — "Nothing is created if any entry is bad" — which tells the agent a single bad cube aborts the whole batch. It does not say what is returned or whether bones must pre-exist.

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?

Four short sentences, each carrying a distinct rule, with the mandatory geometry-choice guidance front-loaded ahead of the model-specific UV advice. There is no filler; the only weakness is that the terse phrasing assumes familiarity with GeckoLib/Java model formats.

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 mutation tool with no output schema and a 12-field nested cube object, the description covers the geometry and UV rules and the failure mode, but leaves gaps an agent would want: what the call returns, whether the cube lands in the current tab/project, and whether the referenced bone must already exist. Adequate but not complete.

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?

Top-level schema description coverage is effectively 0% (the single "cubes" property is undocumented), so the description must carry the load and largely does: it explains the mutually exclusive corner/size pairs, the per-model requirement for bone and faces, and the box-UV sizing constraint for uv_offset. It stops short of explaining names, pivot, rotation, mirror or inflate, which only the nested schema covers.

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 opens with a specific verb and resource ("Adds cubes") and immediately distinguishes two geometry conventions — blockbench from/to or origin/size — as well as GeckoLib box-UV versus Java per-face-UV models. It is clearly separable from the sibling add_bones, though it never names that sibling or any other alternative.

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 concrete selection rules: use from+to or origin+size, give each cube its own uv_offset for GeckoLib so UV islands do not overlap, and use faces only for Java models, which also need no bone. What is missing is when NOT to call it, or whether a target model/tab must already be open — no exclusions or prerequisites are stated.

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