sweep_rotation

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

With no annotations, the description carries the load and does disclose key mutation behavior: it rotates geometry in steps and then restores positions. It also explains collision reporting and optional min-distance reporting. It omits cost/step-count implications and error behavior, keeping it below a 5.

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?

Purpose and behavior are front-loaded in the opening sentence before the Args list, and every line of the Args block adds parameter meaning. Slightly verbose but nothing is wasted.

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 9-parameter geometric-sweep tool with an output schema (so returns needn't be described), the description covers the rotation mechanics, restoration guarantee, and filtering semantics adequately. Missing only performance/step-count guidance and failure modes.

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 coverage is only 11%, so the Args block does real work: it explains format ("x,y,z" in mm), semantics of moving vs against ('empty = everything else'), and measure_to's purpose. Only 'instance' is left to its schema description and defaults aren't restated, so not a full 5.

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+resource (rotate occurrences about an axis in steps and report collisions at each angle) and grounds it with concrete examples (door hinge, lock tongue). This clearly distinguishes it from single-check siblings like check_interference.

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 concrete examples (checking a door opens 0–110°, a lock tongue turns freely) convey when the tool applies, and 'Positions are restored afterwards' signals safety of use. It doesn't explicitly name check_interference as the single-angle alternative, so it stops short of full when/when-not routing.

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