rupa_cad_fillet

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

Even though annotations already mark this as destructive, the description goes well beyond that by disclosing a dangerous kernel behavior: fillet can return ok with a corrupted solid that adds material, and this tool guards against it via two independent validators. It also states that failed results are never saved, which is essential safety context for an agent.

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 front-loaded with the action and selection modes, followed by a measured, technically specific warning. The warning paragraph is long but earns its place because it prevents the agent from trusting a successful-looking but corrupted operation.

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 mutation tool with seven parameters and no output schema, the description plus input schema cover selection modes, safety thresholds, overwrite semantics, and failure behavior. The only minor gap is that the success return payload is not described, but this is less critical for a mutating tool and the safety disclosures are unusually complete.

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 already high (86%), so the description does not need to re-document parameters. It adds meaningful semantic value by explaining the safety boundary for `ukuran` with a concrete 10x20x30 example and by showing how edge selection modes relate to `tepi`, `arah`, and the all-edges default.

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 states a concrete action ('Bulatkan (fillet) atau serong (chamfer) tepi') on a specific resource (CAD edges), and enumerates the three selection modes: all edges, edges along a direction, or an explicit index list from `rupa_cad_tepi`. This makes the tool's scope unambiguous and separates it from the related edge-listing sibling.

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 gives explicit when-not-to-use guidance: for fillet above half the smallest side, it warns that results can be corrupted and the tool rejects them, then directs the agent toward `chamfer` as the clean-failing alternative. It also clarifies the three edge-selection modes, so an agent can choose the right call shape.

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