sweep

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

With no annotations at all, the description carries the full behavioral burden, and it does disclose a real geometric precondition: the profile should sit at the path start and be roughly perpendicular to the path. It does not say what happens on failure, whether existing geometry is consumed, or whether path_sketch and path_points are mutually exclusive, leaving substantive gaps for a geometry-creating operation.

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?

Three sentences, front-loaded with the action, and each carries information: what is swept, the path alternatives, the orientation precondition, and a use case. No filler, though the path-alternative clause is slightly parenthetical.

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?

An output schema exists, so return values need no explanation, which lowers the bar. Still, for a 7-parameter tool with zero schema descriptions and no annotations, the description leaves the agent guessing about frenet, material and whether a path is required at all — a meaningful gap before invocation.

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, and it partially does: it explains profile_sketch, names path_points explicitly in backticks, and clarifies that the path may be 'a sketch of connected edges'. Four parameters — doc, result_name, frenet and material — receive no explanation anywhere, so compensation is only partial.

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 and resource ('Sweep a closed profile sketch along a path') and defines what the path can be, so the agent knows exactly what geometry operation this performs. It does not contrast itself with nearby modelling siblings such as loft, extrude_polygon or revolve, which is the only thing keeping it from a 5.

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?

'Use for pipes, rails and cable runs' gives a concrete application context that tells the agent when this is the right modelling op. It stops short of naming alternatives (e.g. use loft when the profile varies along the path) or stating exclusions, so it is clear context without routing guidance.

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