sketch_transform

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

With no annotations, the description carries the full burden and does substantial work: it declares atomicity ('All or nothing'), warns that the constraint solver may pull entities back so results must be verified, and discloses the return payload shape including the entities-vs-created branch on `copy`. It does not spell out failure/rollback semantics or ref format details, keeping it 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?

Purpose is front-loaded in the first sentence, the solver caveat and return shape follow, and the example closes it out. Every sentence carries information an agent needs; nothing is padding despite the multi-line layout.

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 mutation tool with no annotations and no output schema, the description supplies the missing return contract and the key behavioral risk (solver-driven geometry changes). Minor gaps remain around entity-ref syntax and the 500-item limit, which the schema covers only implicitly.

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 already 86%, but the description adds genuine semantics beyond it: the rotate-then-translate ordering as a pipeline, the meaning of `copy=true` (originals kept, new entities under `created`), and a concrete call showing `translate=[30,0]` semantics. That goes past the schema's per-field 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?

Opens with a specific compound verb plus resource ('Move/rotate sketch entities (or copies of them)') and immediately pins the exact transform order (rotate about `about`, then translate). This distinguishes it from siblings like sketch_mirror, sketch_pattern, and sketch_offset, which also duplicate/move geometry, without needing 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?

Usage is implied through the worked example (copy a circle 30 mm right) and the `copy` flag, giving an agent a concrete pattern to imitate. However there is no explicit 'use this instead of sketch_pattern/sketch_mirror' routing, and no stated prerequisites beyond that `sketch` comes from sketch_create.

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