rebuild_feature

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

With no annotations, the description carries full responsibility for behavioral disclosure. It clearly reveals that the tool captures inputs, deletes the feature, recreates it from the current sketch, selects profiles by area proximity, and returns ok=false with a WARNING if deletion succeeds but recreation fails. It also indicates traversal semantics across root and sub-components.

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?

Although long, the description is well-structured with labeled sections: supported classes, error/recommendation behavior, profile matching, failure mode, args, and chain pattern. The opening sentence leads with the core purpose, and every section provides decision-relevant detail without fluff.

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 a destructive two-step tool with no output schema and no annotations, the description covers supported inputs, alternative strategies, failure handling, profile-matching heuristics, and troubleshooting/undo guidance. This gives an agent sufficient context to invoke and recover from failures correctly.

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?

The input schema has 0% description coverage, so the description must compensate. It does: feature_name is documented as walking root and every sub-component, and component_name is described as an optional disambiguation hint. This adds meaningful usage context beyond the schema types.

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 opens with a specific verb and resource: 'Rebuild a feature whose downstream references are stale (G10) by capturing its inputs, deleting it, and re-creating from the current sketch.' It also enumerates supported feature classes and distinguishes this operation from other modeling tools.

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 explicitly tells when to use the tool (broken extrudes with stale cached geometry), when not to use it (fillet/chamfer/hole/revolve), and what to do instead: suppress fillet/chamfer features, or delete and re-create others via appropriate add_* tools. The chain pattern further clarifies its role in a broader repair workflow.

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