feature_loft

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

With no annotations present, the description carries the full behavioral burden and does so thoroughly: it documents units, end-condition semantics, cross-parameter constraints, the exact error classes (INVALID_PARAMS with nothing changed vs FUSION_API_ERROR with timeline rollback), and the complete return structure including created/modified/removed bodies and health state.

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 long but appropriately sized for a 9-parameter, annotation-free CAD operation. It is front-loaded with purpose, then logically structured into sections, end conditions, guides, closed/is_solid behavior, units, errors, returns, and examples, with no filler sentences.

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's complexity, the absence of annotations, and the lack of an output schema, the description is complete enough to call the tool correctly: it covers inputs, constraints, error behavior, side effects, and return values, and even provides concrete examples.

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?

Although schema coverage is already 100%, the description adds meaningful cross-parameter semantics beyond the schema: it explains that units apply only to {sketch, point} profile specs, that inner sections default to free, that closed requires 3+ profile sections with no point section, and how point_* conditions are restricted to point sections. These constraints are not obvious from the individual parameter descriptions alone.

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 states a specific verb and resource: 'Loft a solid through two or more sections', with concrete examples like transitions, ducts, bottle necks, and domes ending in a point. This makes the core operation clear, but it never explicitly contrasts the tool with siblings such as feature_sweep or feature_revolve, so the agent must infer the distinction from the domain language alone.

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 rich context for when the tool applies and includes several usage constraints (rails never with a centerline, closed needs 3+ profile sections, point sections only at the ends, is_solid=false only for new_body/new_component). It does not name explicit alternatives like feature_sweep or feature_extrude, so it stops short of the 'when to use vs alternatives' clarity that would earn a 5.

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