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

Goes well beyond the annotations: cost ('Free'), latency ('runs at once'), reversibility ('can be undone the same way'), write scope ('writes only their own record'), and the result shape ('ordinary result, not a plan_token'). The one real gap is whether a new call replaces or adds to a prior selection — for a 'select' tool that is the key behavioral question left unanswered.

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-loaded with the action and the unmark inverse, then the usage constraint, then the confirmation policy. The uppercase CONFIRMATION block is somewhat verbose and partly discusses other tool classes, but each part carries decision-relevant information rather than filler.

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?

No output schema exists, and the description partially compensates by describing the return as an ordinary result rather than a plan_token. Coverage of cost, timing and undo is strong; the missing replace-vs-append behavior is the remaining hole for a mutation tool with only three parameters.

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 the schema already documents order_id, variants and the 'Default true' on selected. The description's only genuine addition is that selected=false performs an unmark, which is meaningful but minimal beyond the schema baseline.

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+scope: marks variant(s) the person chose within an order, and immediately clarifies the inverse with 'selected=false unmarks'. An agent can distinguish this from creative_order or creative_get 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?

Explicit gating rule: 'The model never chooses for the person — call this only on their word.' It also states the contrasting rule for other classes of action ('Everything destructive, outbound or financial still proposes and waits'), so the agent knows when this immediate-execution path applies and when it does not.

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