geometry_manage

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

With no annotations, the description carries the disclosure burden. It does reveal important side effects: scaffold_polygon_2d 'Instantiate and attach' to the active scene and generate_mesh 'attach to scene or save.' However, it does not mention whether the pure geometry ops (boolean, offset, triangulate, hull) have side effects, nor does it discuss permissions, reversibility, or failure modes. The compatibility-alias note is useful.

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 description is longer than average, but it is efficiently structured: a one-line summary followed by a compact op list with call signatures. Every line contributes. The canonical call shape note is important and not padding. It could be slightly tightened, but it earns its length.

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 tool with six operations and no annotations, the description covers all operation signatures, defaults, and key side effects. It does not explain prerequisites like requiring an active scene for scaffold/generate_mesh, and return values are not mentioned (though an output schema exists). Still, it is largely complete for an agent to invoke correctly.

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 compensate. It does thoroughly: each op lists its parameters with defaults and expected inputs, e.g., polygon_boolean(operation='merge', poly_a=[...], poly_b=[...]), polygon_offset(polygon, delta, join_type), scaffold_polygon_2d(parent_path, points, polygon_name, is_collision, color). This is exactly the meaning the generic 'params' object in the schema lacks.

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 clear domain statement ('Constructive 2D Solid Geometry and Procedural 3D Mesh Generation') and then enumerates six specific operations with verbs like polygon_boolean, triangulate, and generate_mesh. This makes the tool's purpose and scope evident, and it distinguishes itself from sibling tools such as mesh_manage by focusing on geometry construction/procedural generation rather than asset management.

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 implies usage through the operation list and the canonical call shape, but it never explicitly states when to choose geometry_manage over alternatives, nor does it mention exclusions or when-not conditions. It provides call formatting guidance but not situational routing.

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