shell

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

With zero annotations the description carries the full load and does so well: it discloses units (mm/degrees), that each call either ends with an active feature or is rolled back, and that nothing persists unless model_save is called. It also explains the two behavioral modes of the operation (with remove = open faces, without remove = closed hollow body; outside = wall grows outward). It stops short of covering failure behavior for invalid thickness or face references.

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?

Sentences are dense and mostly earn their place, but the structure is inverted: environment boilerplate and cross-tool guidance lead, while the tool's own operation is the last paragraph. Front-loading the hollowing semantics would materially improve scanability without adding length.

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 mutation tool with no annotations and no output schema, the description supplies the essentials an agent needs to call it safely: units, coordinate conventions, addressing rules, save/rollback semantics, and a verification path through model_info and preview_image. Remaining gaps (error modes, thickness limits) are secondary.

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 40%, so the description must compensate, and it does for the two behavior-critical parameters: remove is explained as faces to open with the surface:N format and a concrete example via find_geometry normal=+y, and outside is explained as outward vs inward wall growth. thickness is only obliquely covered by "wall thickness" and feature_name is left entirely to the 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 actual purpose appears only in the final paragraph: "Hollow the part with wall thickness," which is specific. The opening sentence ("Creates/edits geometry in the running Creo 5...") is generic boilerplate that would apply equally to extrude, revolve, or sweep, and it is positioned first, so an agent skimming the description gets no sibling differentiation until the last block.

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?

There is real guidance—use symmetric extrudes/revolves/patterns because no mirror tool exists, and verify with model_info (volume, bound_box) and preview_image—but most of it targets other operations rather than routing the agent to shell versus hole/round/chamfer. No explicit when-not-to-use condition or prerequisite is stated for the hollow operation itself.

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