add_fillet

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

With no annotations, the description carries the behavioral burden. It discloses that the operation applies to the current part, uses a single constant radius, and returns the number of filleted edges and resulting mass properties. It does not mention irreversibility or failure modes, but the key side effects and outputs are visible.

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?

Three sentences cover purpose, edge syntax, and return value with no fluff. The most important selection semantics are front-loaded immediately after the one-line purpose.

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 mutating CAD tool with no output schema and no annotations, this is nearly complete: purpose, edge modes, defaults, and return behavior are all present. The only gap is the absence of any note about the optional name parameter or explicit prerequisites beyond 'current part'.

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 description coverage is 0%, so the description must compensate. It thoroughly explains the non-obvious edges parameter syntax ('all', x/y/z, explicit indices) and notes that radius is in mm. Only the optional name parameter is left undocumented.

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 ('Round') and resource ('edges of the current part'), and clarifies that it uses one constant radius in mm. It is clearly distinct from the sibling add_chamfer by operation intent, but it does not explicitly name alternatives, so sibling differentiation is implicit rather than explicit.

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 edge-selection instructions and the reference to list_edges imply a practical workflow for operating on an existing part. However, it does not state when to prefer this over add_chamfer or other modification tools, nor does it give prerequisites or exclusions.

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