check_interference

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

With no annotations, the description carries the behavioral burden and does well: it defines the unit (mm^3), excludes touching faces with a concrete example, and explains the meaning of count == 0. It stops short of stating whether the tool is read-only or how strict the overlap tolerance is, but the core behavior is clear.

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 short, well-structured sentences lead with the main purpose, add the critical touching-face exclusion, and end with the count interpretation. Every sentence earns its place and no unnecessary details are included.

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 zero-parameter analysis command, this is complete: an agent knows what is returned (overlapping component pairs and volumes), how to interpret count, and what edge case (touching faces) is deliberately excluded. No output schema exists, but the description covers the essential return contract.

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 tool has zero parameters and the schema accurately reflects that, so there are no parameter semantics to document. The description still adds value by describing the output semantics (per-pair overlap volume and clash count), which is useful in the absence of an output schema.

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: 'Report component pairs whose solids overlap, with the volume in mm^3.' This clearly identifies it as an interference/clash analysis tool and separates it from the creation/getting siblings such as add_box or get_mass_properties, which do not report pairwise overlaps.

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?

It implies this is the tool to use for clash detection and gives an interpretative rule (count == 0 means clash-free), but it never explicitly states when to call it versus alternatives or what conditions apply, such as requiring an open assembly or a prior rebuild.

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