create_lattice

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

With no annotations, the description carries the burden and does so for the key behavior: the lattice is fitted to the bounding box and a Lattice modifier is added, revealing this is a non-destructive, modifier-based operation rather than a baked edit. It also lists the return dict contents. Gaps remain around failure modes (missing/hidden object, existing lattice, unsupported object types beyond the hint 'mesh, curve, text...').

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 a short mechanism paragraph, then structured Args/Returns. Every arg note adds real information, though the interpolation paragraph is longer than strictly necessary for a routing decision.

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?

Output schema exists, yet the Returns note still gives the agent a usable summary, and all four parameters are covered. For a modifier-creating mutation with zero annotations, remaining holes are error behavior and prerequisites (object must exist/be selected, whether the modifier persists unapplied).

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%, so the description must carry everything, and it does: resolution is bounded (2 to 64 per axis) with its meaning and effective default [2,2,2] (the schema default is null), and interpolation is explained by effect with a concrete numeric example (scale to 0.5 halves the shape; BSPLINE gives ~0.67). lattice_name's default naming pattern is also spelled out.

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 combination: fit a lattice cage to an object's bounding box and add a Lattice modifier for whole-shape deformation. The final clause explicitly separates the creation step from the editing step (move_lattice_points), so an agent can tell it apart from the sibling that actually deforms points.

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 names the follow-up tool and the condition that selects it ('bend, taper or bulge the whole shape with move_lattice_points instead of editing vertices'), which routes the agent correctly. It stops short of stating exclusions (e.g. when not to use a lattice at all, or prerequisites on object state), but the workflow context is clear.

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