Shape push pull

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

Annotations already declare mutation and non-idempotency (readOnlyHint=false, idempotentHint=false), and the description adds real value beyond them: the sign convention (negative carves, positive extends), that the operation mutates existing solids, and implicit units via the '0.5 m' example. It doesn't mention undo/reversibility despite a sibling shape_undo existing, so it falls short of the top band.

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, purpose front-loaded, then face-resolution rules, then an example that anchors the mental model. Dense but every sentence earns its place; the long parenthetical about normals is the only slightly heavy patch.

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 5-parameter mutation tool with no output schema and low schema coverage, the description covers the operation, its direction semantics, target resolution, and applicability to derived geometry, which is enough to call it correctly. Missing items are minor: the 'name' parameter and any return/confirmation detail.

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 only 20% (only 'face' documented), so the description must compensate, and it largely does: it explains face normal syntax (+x/-x/... or [nx,ny,nz]), how 'point' disambiguates among coplanar faces (nearest wins, else outermost), and the sign meaning of 'distance'. The 'name' parameter remains entirely unexplained.

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 ('push/pull a flat face of a node') and immediately distinguishes itself from neighbors like shape_extrude_sketch and shape_transform by naming the SketchUp-style face-editing operation. An agent can tell what it does without opening the 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?

Gives clear operative context: what counts as a face, how the coplanar region is resolved, and that it works on any node including results of earlier push/pulls and booleans, plus a concrete worked example. It stops short of explicitly naming an alternative (e.g. shape_extrude_sketch) for when a full extrude is preferable.

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