rock

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

Annotations only declare the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), so the description carries the rest and does so well: determinism ('Same seed, same rock'), that the mesh is closed, that the object origin sits at the bottom centre so the rock stands on the ground, and that the output passes check_mesh. It does not say whether the new object is added to the scene/selection or what the return payload is, which keeps it from a 5.

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?

Front-loaded with the one-line purpose, then one clause per parameter with no filler. Every sentence carries usable information: the 'same seed, same rock' line, the low-poly recipe, and the origin/ground-contact note all change how an agent would call it.

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 an 8-parameter, no-output-schema generation tool, the description covers geometry, determinism, scale semantics, shading mode, placement and validation. The remaining gap is scene-side behavior (is the object selected, returned, or only added by name) and the meaning of the required 'name' parameter.

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% with 8 parameters, so the description must compensate and does: it defines radius (half-width; X/Y extent = 2x radius), roughness (0–1 departure from a ball), flatness (0 to below 1, 0.5 = flat boulder), detail (1–5 with triangle counts 20/80/320/1280), facets (flat vs smooth shading), at (bottom-centre world placement) and seed (reproducibility). Only 'name' is left undefined, which is self-evident.

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+resource: 'Make a closed rock mesh: an icosphere roughened by noise and squashed.' That distinguishes it from siblings like blob, create_primitive, terrain and sculpt, which produce different geometry. The construction method (icosphere + noise + squash) is explicit enough that an agent knows exactly what object it will get.

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?

Gives concrete selection guidance: 'For a low-poly game use detail 1 or 2 with facets=true' and 'Vary seed, radius and flatness to make a set of different stones.' It also implies the quality gate ('The mesh passes check_mesh'). It stops short of naming a competing sibling (e.g. blob or terrain) or stating when NOT to use this tool, so it is clear but not exhaustive.

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