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

Goes well beyond destructiveHint=true: it explains that the underlying file is only deleted when no other line, quote or order references it, which is exactly the consequence an agent needs before calling. It also discloses the refusal condition and the auth requirement (connection prompts sign-in on printdash.io when unauthenticated).

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, front-loaded with the action and scope, with no filler. The parenthetical 'side for one face only' is slightly compressed but still parseable; nothing is wasted.

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 destructive nested-target tool with an output schema, this covers what the description must carry: what gets removed, what gets deleted from storage, when the operation is refused, and what auth state is needed. Nothing essential for a correct call is missing.

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% and already documents kind/id/side/design, so the baseline is 3. The description adds cross-parameter interaction semantics the schema only partially conveys: 'no side' means every file on a one-design job, while side applies only for a single face, and design selects among multiple designs.

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 ('Takes artwork off a line') and immediately scopes what unit is removed: one design's file, a single side, or every file on a one-design job. That distinguishes it cleanly from attach_artwork* tools and from remove_cart_line, which removes the line rather than its artwork.

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 an explicit when-not condition ('Refused when the line's artwork can no longer change') and clarifies the granularity choice between single-file removal and whole-job removal. It never names a sibling alternative (e.g. use remove_cart_line to drop the line itself), so routing is implied rather than prescribed.

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