inspect_part

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

With no annotations, the description carries the full burden and does disclose the key behavioral traits: it is read-only in effect ("Does not move parts or change the camera"), faces are paginated at 1..500 per type, and face names are temporary references rather than stable IDs. It omits any mention of permissions, error conditions, or what the response actually contains.

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?

Five short sentences, front-loaded with the purpose before the sequencing advice and the pagination caveat. Little waste, though the define_interface aside sits slightly awkwardly between the read-only disclaimer and the pagination detail.

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 five-parameter tool with no annotations and no output schema, the description covers behavior and paging but not the return shape or the two required identity parameters (doc_name, part). An agent can call it, but must guess at the response structure and at how part is identified.

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% across five parameters, so the description must compensate, and it explains pagination and the offset semantics. However, it names the offsets as next_plane_offset/next_cylinder_offset while the schema calls them plane_offset/cylinder_offset, and it says nothing about doc_name, part, or the exact meaning of feature_limit, leaving two required parameters completely unexplained.

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 first sentence names a specific verb (inspect) and the concrete resources returned (valid world-space geometry, planar faces, cylindrical hole candidates), which is far more than a restated name. It does not explicitly differentiate itself from the sibling inspect_region, so the boundary between the two inspection tools is left to inference.

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?

"Start here before assembly work" gives a clear sequencing rule, and naming define_interface as the follow-up for persistent face binding is genuinely useful routing. It also points at feature_counts for full totals, implying the paginated path is for enumeration only, but it never states when inspect_region would be preferred instead.

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