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

Goes well beyond the annotations by declaring the operation order (percentage, then flat, then rounding) and why it matters, the PREMIUM/license gate, and a precise error contract: it never raises a protocol error but returns {"error": ...}. Annotations already cover read-only/idempotent, and the description reinforces retry safety after correcting input.

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 action and the order-of-operations caveat, and every sentence carries signal (order, example, sibling exclusion, error contract). The embedded JSON example is long but earns its space by demonstrating charm_ending behavior; minor verbosity from repeated formatting.

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?

Covers everything an agent needs: what it does, when to use it vs a sibling, parameter ordering semantics, error envelope shape, licensing constraint, and retry safety. With an output schema present, the description need not fully re-document return values, and the example suffices.

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 parameter definitions are already provided; the description nonetheless adds value by stating the pipeline order that determines the result and by showing charm_ending applied after rounding in a worked example. It stops short of adding syntax or edge-case rules beyond that example.

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 (apply one pricing rule across a list of prices) and the immediate effect (show the effect), backed by a concrete input/output example. It also names payout_estimate as the tool it is not, so an agent can distinguish it from siblings 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 when-to-use ('repricing a catalogue before export') and an explicit exclusion with the correct alternative ('Not for what a price nets you after Shopify's fees: that is payout_estimate'). That is the full when/when-not/alternative triad.

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