feature_fillet

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

No annotations exist, and the description carries the full burden well: it discloses that a missing mode field or non-edge ref yields INVALID_PARAMS with nothing changed, that variable/chord on an old Fusion API yields FUSION_API_ERROR 'not available', and that a computed error rolls the timeline back. Staleness of edge refs and the units/expression semantics are also explicit.

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 core action, then organized into modes, units/refs, errors, return shape, and examples. Dense but nearly every clause carries information; the mode paragraph is slightly telegraphic at the cost of readability.

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 11-parameter mutation tool with no annotations and no output schema, the description supplies the mode contract, error taxonomy, rollback semantics, and an explicit return-value shape, plus two worked examples. An agent can call this correctly without opening the schema.

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 the baseline is 3; the description adds value beyond it by explaining the cross-field mode contract (radius vs. start_radius/end_radius/mid vs. chord_length), the 0..1 position convention, and that strings are Fusion expressions. It does not cover corner or tangent_chain, but those are documented in the schema.

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 ('Round edges of a body with a fillet') and immediately decomposes the tool into its three modes, which distinguishes it from feature_chamfer, feature_rule_fillet and timeline_edit_fillet without naming them.

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 maps each mode to its required fields and notes that fields of another mode are refused, so the agent knows how to pick a mode. It also directs the agent to obtain edge refs from inspect_query and warns to re-query after later features. It does not state when to prefer this tool over the sibling fillet tools (feature_rule_fillet, timeline_edit_fillet), which keeps it short of a 5.

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