add_relief

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 well: it discloses that raised relief becomes a new part (colored by filament=N) while engraved relief becomes a negative part, that it wraps around curved faces keeping size along the surface, and that it recommends a preview afterward. It omits failure modes, whether the original object is modified, and any permission/error behavior, so it falls short of 5.

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 purpose sentence is front-loaded, followed by a compact parameter glossary and a closing tip. It is dense but every line carries information; the only mild bloat is the repeated curved-face explanation, which could be trimmed.

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 an 11-parameter tool with no annotations, no output schema, and zero schema coverage, the description supplies the semantics an agent needs for most parameters and the raised-vs-engraved model. The unexplained required 'object' parameter and the unmentioned 'font' / text-vs-svg precedence 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 0%, so the description must compensate, and it largely does: it defines face (with the six enumerated values and 'the side it is read from'), at ([x,y,z] plate point, defaulting to the face center), size (cap height for text, longest side for SVG, in mm), depth, rotate, engrave, and filament. It leaves 'object' (the sole required param) and 'font' undefined, which keeps it from a 5.

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 names a specific verb and resource ('Text or an SVG logo on a face of an object, raised or engraved') and draws a clear analogy to Bambu Studio's Text and SVG tools. It also names the closest behavioral relatives (add_shape/add_modifier are implicitly distinguished by the text/SVG focus) and the follow-up sibling preview_plate, so an agent can tell it apart without opening the schema.

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 gives clear context for when to use it (adding text/SVG to a face, raised or engraved) and explicitly points to preview_plate afterwards, plus set_part_type to revert an engraving. It stops short of naming an alternative tool to use instead (e.g. add_modifier or boolean_objects) or stating exclusions, so a 4 rather than a 5.

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