add_shape

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

With no annotations, the description carries the full burden. It does disclose a non-obvious side effect: base > 0 creates a separate part named 'Base' with its own filament, and base_filament 0 means inherit the text filament. It does not state units for most dimensions, whether objects are placed at the origin or at x/y, or what the tool returns, so the safety/placement profile remains incomplete.

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 verb and the shape list, then per-shape parentheticals that each carry real information rather than filler. The density is justified by 18 parameters, though the text/svg clauses become long and would read better as separate lines.

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 18-parameter mutation tool with no annotations, no output schema and no schema descriptions, the description covers shape semantics well but omits object placement (x/y), the meaning of plate and filament indices, and any return value. It is adequate to build a solid but not to fully predict the result.

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 does for most parameters — including disambiguating the overloaded `height` (box height vs. depth of text letters vs. raised height for svg) and explaining text_height, base, base_filament, font, svg and size semantics. Gaps remain: x, y (placement), name, plate and filament indices are never mentioned.

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?

States a specific verb and resource ("Create a simple solid") and then enumerates the exact shape families supported (box, cylinder, cone, sphere, text, svg) with their governing dimensions. An agent can immediately tell this is the primitive-creation tool and, via the closing sentence, how it differs from add_relief.

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 routes the agent to add_relief for putting text or a logo on an existing object, which is the key sibling ambiguity. It does not cover other plausible alternatives (import_model, add_modifier) or prerequisites such as an open project, but the main exclusion is stated clearly.

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