inspect_bounding_box

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

With no annotations at all, the description carries the full burden and does disclose meaningful behavior: the tight/loose fallback from Fusion's measure manager, the 'tight': false flag, and the union-of-bodies rule for components and occurrences. It also flags that an 'errors' array can be returned, though it never explains what lands there or whether partial results still come back.

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 scope sentence is front-loaded and the return shape plus example are compact. Minor waste in the odd inline quoting of `"tight": false` and the trailing newline-only example, but every block (behavior, return shape, example) earns its place given there is no output schema.

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 read-only inspection tool with no output schema and one fully documented parameter, the description supplies the return structure, the aggregation semantics, and the coordinate unit — enough to call it correctly. The underspecified 'errors' contents and the absence of any note about cost on large models are the remaining gaps.

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 100% and the single 'refs' parameter is fully documented in the schema, including the default of all visible bodies. The description adds no syntax, ordering, or deduplication semantics for refs beyond what the schema already states, so the baseline 3 applies.

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 resource and coordinate convention ('World-axis bounding boxes in mm') and explains when a tight vs loose box is produced, so an agent knows exactly what is computed. It does not explicitly contrast itself with inspect_physical_properties or measure_distance, 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?

Usage is only implied: the example 'inspect_bounding_box() -> overall size of the model' hints at the zero-argument case, and the schema default ('all visible bodies') implies scope. There is no explicit statement of when to prefer this over measure_distance or inspect_physical_properties, and no exclusions.

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