extrude_sketch

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

With no annotations the description carries the full burden, and it does disclose real behavior: the result is merged with the body, the sketch keeps its dimensions/relations (a non-destructive claim about authored geometry), the return is mass properties, and it hints at failure semantics ('the refusal names a point ahead'). It omits whether the operation is purely additive and what preconditions (active part, valid sketch) apply.

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 is front-loaded, but the body is a run-on of nested parentheticals and asides ('e.g. one a person drew', 'so the person's design stays in charge') that make the mode logic harder to scan than it needs to be. Information density is high, yet the structure could be tightened without losing content.

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?

With no annotations, no output schema, and five undocumented parameters, the description supplies a lot: modes, direction, return value, and sketch preservation. It remains a bit short on preconditions and on the 'name' argument for a tool whose siblings imply richer feature-graph behavior.

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 well for three of five parameters: depth_mm is 'along the sketch's normal', reverse=True goes the other way, and up_to accepts 'next' or a '@x,y,z' point with distinct behaviors. The 'name' parameter (feature naming, default 'Extrude') is never explained, leaving one gap.

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 gives a specific verb+resource ('Extrude an existing sketch of the current part by name'), and the qualifier 'existing sketch' implicitly distinguishes it from siblings like add_extruded_profile that create new geometry. It does not name any sibling outright, so the differentiation is inferred rather than stated.

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 selection logic among modes: depth_mm along the normal, or up_to='next', or up_to='@x,y,z' when 'next' fails, plus the prerequisite 'read_sketch shows it first'. It never says when to prefer this tool over cut_sketch or add_extruded_profile, so the routing guidance is incomplete.

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