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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely new behavior: it never raises a protocol error, returns an {error: ...} object instead, and is always safe to retry after correcting input. The PREMIUM (license) note also flags an access prerequisite an agent would otherwise only discover at call time.

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 core definition, then example, then usage routing, then error semantics — a sensible order with little waste. The multi-line inline JSON example is slightly bulky but earns its place by demonstrating output fields.

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?

With an output schema present the description needn't document return values, yet it still previews them in the example, and it covers inputs, routing, licensing, and error/retry behavior. Nothing an agent needs before calling 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%, so baseline is 3; the worked example lifts it by showing how the inputs map to distinct outputs (break_even vs suggested_threshold vs above_current_aov_by) and confirming target_uplift_pct=0 collapses to break-even. It doesn't explain units/edge behavior of target_uplift_pct beyond the default, so not a 5.

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 ('Find the order value at which free shipping stops costing you money') and immediately operationalizes it as break-even math. It explicitly names the sibling it is not (rate_card) and the condition that separates them, so no schema comparison is needed.

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?

"Use when setting or defending a free-shipping bar" plus "Not for what shipping should cost when it is not free: that is rate_card" gives an explicit when/when-not with a named alternative. It only disambiguates against one of five siblings, leaving dim_weight/freight_class/landed_cost/parcel_fit to inference (though those are far enough apart to be low risk).

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