chamfer_solid

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

With no annotations to rely on, this description carries the full behavioral burden and does so excellently. It discloses that ONE point per edge is required, that the edge nearest the camera wins (view-dependent selection), and that the actual removed volume is slightly less than the idealized formula due to intersection with other edges. This is exactly the kind of non-obvious behavior an agent must know.

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 four sentences long, each earning its place: purpose, parameter format, selection caveat, and verification tip. It is appropriately dense without being bloated. A minor deduction because the volume formula might be overly technical for upfront placement, but the structure is still effective.

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?

Given the tool's complexity (3D solid chamfer with view-dependent edge selection), the description covers the critical operational context: edge specification, camera behavior, and practical validation. It doesn't spell out the exact meaning of 'distance' in words, but the output schema is present so return values are already handled. This is a well-rounded description for a non-trivial 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?

The schema only provides types (array of arrays of number for edges, number for distance) with no descriptions. The description adds meaning by explaining edges as [[x,y,z], ...] with one point on each edge, and infers the distance parameter via the volume formula (distance^2/2 * length). It doesn't explicitly define distance as the setback length, but the context makes it reasonably inferable.

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 the specific action ('Chamfer edges of a 3D solid') and clearly identifies the resource (edges of a 3D solid). It distinguishes itself from related tools like fillet_solid (rounded edges) and chamfer_polyline (2D), making the purpose unambiguous.

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 practical usage guidance: it compares 45-degree chamfers to fillets for print support, advises setting the view (view_3d) when the target edge is hidden, and recommends verifying with solid_volume. While it doesn't explicitly state when to use chamfer_solid vs. alternatives, these contextual tips clearly help an agent decide and operate correctly.

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