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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=true), and the description adds meaningful context: it authors via the public API, returns patched source plus evaluation diagnostics, and scopes itself out of pole extraction. It doesn't mention failure modes (invalid radius, unresolvable selector) or what happens if the blend cannot be evaluated, which is the remaining gap.

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?

Four sentences, front-loaded with the when-to-use condition, and each sentence carries distinct information (purpose, mechanism/return, selector forms, out-of-scope). The API-signature sentence is slightly dense but earns its place by mapping parameters to the emitted call.

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 7 parameters, rich annotations and an output schema, the description covers purpose, mechanism, selector semantics, and scope boundaries, so an agent can invoke it correctly. Missing only error/edge-case behavior (unresolvable selector, blend failure) which would matter for a mutation tool that patches source.

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 baseline is 3; the description adds value by showing the underlying call form Shape.fillet(radius, selector, { continuity }) / Shape.chamfer(distance, selector), which clarifies how radius/distance/selector/continuity pair up. It also spells out the EdgeSelector forms (canonical refs/query strings vs { face: ... }) and that G2 applies only to fillets — though much of this repeats schema text.

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+resource: authoring (inserting) a fillet or chamfer blend on a kernelCAD Shape via the existing public API. It also explicitly disambiguates from the neighboring NURBS-extraction capability by saying it does not extract blend-surface poles, so an agent can tell it apart from inspect_nurbs-style siblings without opening a schema.

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?

'Use this when you need to author and evaluate a fillet or chamfer' gives a clear triggering condition, and the closing sentence gives an explicit when-not with the alternative described ('kernel surface extraction'). It stops short of naming the concrete sibling tool for extraction, so an agent must infer the handoff, which keeps it from a 5.

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