add_brim_ears

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

With zero annotations the description carries the full load, and it does substantial work: it explains default ear placement, that skipped tips are reported with reasons, that a warning is emitted when a point would weld something, and that radius 0 means Bambu Studio's default of 16 line widths. It does not state the one destructive-ish concern an agent would want — whether existing ears are replaced when keep=false — though 'keep: add to the ears the object already has' implies it.

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?

Front-loaded with the concept, then default behavior, then point overrides, then radius/keep, then a verification workflow — a sensible ordering. The sentences are heavily packed with parenthetical clauses, which costs some scannability, but no sentence is redundant.

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?

No annotations and no output schema, so the description must cover behavior and results; it does cover default placement, skip reporting and warning emission well. The remaining gaps are the undocumented clearance parameter and no statement of what the call returns or whether it requires an already-loaded plate.

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 0%, so the description must compensate, and it explains narrow, small, points (both [[x,y]] and [[x,y,radius]] forms, units in plate mm, warning behavior), radius (including the 0 = default special case) and keep. The notable omission is clearance, a 7th parameter that is never mentioned anywhere, and object is only implicitly the target.

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?

Starts by defining the specific resource ('small round brims only where a part needs them') and contrasts it with the alternative it replaces ('instead of a brim all around'), so an agent can distinguish it from a plate-wide brim setting or a generic brim tool. The add operation is unambiguous from the name plus the defaults/per-points behavior it then describes.

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?

Explicitly states the intended use case — 'Meant for print-in-place and articulated models' — and explains why the alternative fails ('a full brim fills the joint gaps on the first layer and welds them'), which is a real when-to-use/when-not rationale. It also prescribes a verification workflow (preview_plate, slice_project, preview_layer). It does not name sibling remove_brim_ears or any exclusion conditions for non-articulated models, keeping it just short of a 5.

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