Loft

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

Annotations indicate this is a non-readOnly, non-idempotent, non-destructive operation, which the description doesn't contradict. The description adds minimal behavioral context beyond annotations—it mentions 'lofting' profiles but doesn't explain what lofting entails (e.g., creating a smooth transition surface), potential side effects, or error conditions. With annotations covering basic safety, a 3 is appropriate as the description adds some value but limited behavioral insight.

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 a single, efficient sentence with zero wasted words. It's front-loaded with the core action and resources, making it easy to parse quickly. Every word earns its place by conveying essential information without redundancy.

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?

Given the tool has 2 parameters with partial schema coverage, no output schema, and annotations covering basic behavioral hints, the description is minimally adequate. It states the purpose but lacks details on usage context, parameter effects, or expected outcomes. For a modeling operation with multiple 'operation' options, more guidance would be helpful, but annotations provide some safety context.

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 50% (one of two parameters has a description). The description mentions 'two or more sketch profiles', which aligns with the 'profile_sketch_names' parameter's purpose but doesn't add details beyond the schema's minItems constraint. It doesn't explain the 'operation' parameter's semantics or how choices affect the loft result. Baseline 3 is correct as the schema does partial work and the description adds minimal compensation.

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 clearly states the action ('loft') and the target resources ('two or more sketch profiles'), providing a specific verb+resource combination. However, it doesn't explicitly differentiate this from sibling tools like 'sweep' or 'ruled_surface' which might also create surfaces from profiles, leaving some ambiguity about when to choose loft over those alternatives.

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 provides no guidance on when to use this tool versus alternatives like 'sweep' or 'extrude', nor does it mention prerequisites (e.g., needing existing sketches) or context for choosing between the 'operation' options. It simply states what the tool does without usage context.

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