Fillet edges

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

Annotations provide only a title, so the description carries the full burden of behavioral disclosure. It states the action ('Round the selected edges') but does not mention that this creates or modifies a feature, implies write access, or describe any side effects or validation behavior. This is similar to the 'update_drive' example—mutation is implied but not elaborated.

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 two sentences with no fluff. The core purpose is front-loaded, and the edge-selection options are listed compactly. It is efficient and scannable, though the phrase 'Name the edges' is slightly unusual, it does not waste words.

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?

With 13 parameters, no output schema, and sparse annotations, this tool is complex, yet the description only addresses edge selection. It omits context about radius, type, validation, and the overall feature-creation workflow. An agent has to rely entirely on the schema for everything except edge selection, leaving significant gaps in understanding how to call the tool effectively.

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 a minor but useful clarification that the edge selection parameters (edges, query, feature, all, circular) are mutually exclusive alternatives, which the schema does not explicitly state. However, it does not expand on any parameter beyond what the schema already describes, so it only marginally exceeds the baseline.

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 'Round the selected edges,' which is a clear verb+resource statement that unambiguously conveys the tool's purpose of filleting edges. It distinguishes from the sibling onshape_chamfer by using 'round' instead of 'bevel.' However, it doesn't explicitly name the sibling or contrast with it, so it stops short of strong differentiation.

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 implies the tool is for rounding edges but gives no explicit guidance on when to choose it over alternatives like onshape_chamfer or onshape_shell. No exclusions or alternative tool mentions are present. The edge-selection instructions are about how to pick edges, not about when to use the tool.

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