catia_hole

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

Annotations already declare readOnlyHint=false, indicating a modifying operation, and destructiveHint=false, suggesting no destructive side effects. The description adds only the purpose ('create a hole') and capability list; it does not disclose behavioral traits such as requiring an active part, the effect on the feature tree, or failure modes (e.g., point not on face). It also introduces a sketch-based method that has no corresponding parameter in the schema, creating ambiguity about how that method is invoked. With annotations present, the description contributes little beyond the purpose.

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 description is two sentences with no filler. The first sentence states the core purpose and positioning methods; the second lists supported types and options. Information is front-loaded, and every clause adds relevant detail. It is appropriately sized for a tool with 13 parameters and rich capabilities.

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?

The description covers the main purpose and supported hole types but omits several context items that would help an agent call it correctly: it does not explain the sketch-based method in terms of parameters, does not state that the tool requires an active part (though siblings like catia_set_active_body exist), and does not describe the return value or any side effects. Since there is no output schema, the description should at least hint at what the tool returns (e.g., a feature token), but it does not. The schema descriptions partially compensate (e.g., face token guidance), but overall the description leaves gaps for a complex tool.

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 100%, so every parameter has a description. The description adds value by clarifying that x, y, z define a 3D point and that the 'usual case' is point+face, and it mentions an alternative sketch method. However, it does not explain how the sketch method maps to any schema parameter (no sketch token is present), which is a gap. It also does not elaborate on the interplay between hole_type and the head_* parameters, leaving the agent to infer from the schema. Overall, it adds some context but does not fully compensate for the sketch ambiguity.

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 clearly states the verb and resource: 'Create a hole in a face.' It enumerates supported hole types (simple, tapered, counterbored, countersunk, counterdrilled) and depth modes (blind or through), and describes two positioning methods (3D point or sketch). However, it does not distinguish itself from the sibling tool catia_hole_from_sketch, which also handles sketch-based holes, leaving ambiguity about which tool to select for sketch-based workflows.

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?

The description provides minimal guidance: it mentions that point-based positioning is 'the usual case' and that sketch-based positioning is an alternative, but it never explicitly says when to use this tool versus catia_hole_from_sketch. There are no exclusion criteria or alternative recommendations, and the mention of sketch support could mislead an agent into using this tool instead of the dedicated sibling. No guidance is given on prerequisites such as having an active part or the need for a valid face token.

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