loft

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It explains the default behavior (ruled=False produces a smooth surface) and the effect of ruled=True (straight transitions), plus the solid vs. surface output. It does not mention error handling or side effects, but for a CAD loft operation, the disclosed traits are sufficient to set expectations.

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 well-structured and front-loaded: the one-line purpose leads, followed by a helpful contrast with 'pad', then usage instructions, parameter explanations, and an Args list. Each sentence earns its place with informative content, and the formatting improves readability without bloat.

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 loft command with five parameters and an output schema (which presumably documents return values), the description covers the main conceptual points, parameter meanings, and usage context. It could be more explicit about requirements like closed profiles or coplanar sketches, but it already states '2+ profile objects' and that they are 'usually sketches placed at different heights', which is sufficient for an experienced CAD user.

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?

The input schema only provides titles and types, with zero descriptions within the schema itself. The description's 'Args' section adds full meaning for every parameter: 'solid: Produce a solid rather than a surface', 'ruled: Straight transitions instead of a smooth blend', and 'profiles: Names of 2+ profile objects (usually sketches), in order.' This fully compensates for the schema's lack of descriptions.

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: 'Blend between two or more profiles — tapered and organic shapes.' It clearly distinguishes itself from the sibling tool 'pad' by stating that 'pad extrudes ONE profile at a constant section' and that lofts are needed for tapering/blending. This makes the purpose unmistakable.

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 explicitly contrasts with 'pad' and gives concrete when-to-use guidance: 'Real parts taper and blend... Those need a loft.' It also provides ordering instructions ('Give the profiles in order along the blend') and notes that profiles are usually sketches on different planes. This goes beyond simple context by naming an alternative and defining the appropriate scenario.

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