cut_offset_pocket

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

With no annotations, the description carries the full burden and does well: it discloses the through-all default when depth_mm is omitted, how the target face is identified, that the rim follows arcs and splines, that interior holes are preserved, that rim/depth become dimensions, and that mass properties are returned. It omits editability/reversibility of the resulting feature, so it falls short of a 5.

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-loads the core action and constraint in the first sentence, then layers geometry and return-value details. The parenthetical about the I-beam/tray/frame example is slightly digressive, but nearly every clause carries usable information.

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 7-parameter, no-annotation, no-output-schema geometry tool, the description covers the face selection, depth default, outline behavior, and return values ('Returns mass properties'), which is most of what an agent needs. It could still say more about the feature's post-creation lifecycle (edit/suppress/delete).

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 0%, so the description must compensate, and it does for most parameters: face, the (x, y, z) point used to select it, rim_mm, and depth_mm's null-means-through-all semantics. Only the `name` parameter (default 'Pocket') is left unexplained, a minor gap against a 7-parameter 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 ('Pocket a planar face') plus the defining geometric constraint (rim rim_mm wide along the outline). This distinguishes it from the neighboring cut_profile, cut_profile_on_face, and cut_slot siblings, which produce different geometry.

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?

Gives concrete use-case context (recessed web of an I-beam, tray, frame) and a default behavior (depth_mm omitted = through all), which implies usage. However, it never explicitly says when to prefer this over cut_profile_on_face or cut_slot, nor states prerequisites such as the part needing an open planar face.

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