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

Annotations already cover readOnly/destructive/closed-world, so the bar is lower, and the description still adds real context: it is free during validation with no key/credits/wallet, it rejects ambiguous text rather than guessing, and source/input limits apply. It does not explain the non-obvious idempotentHint=false, which is a minor remaining gap.

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 short, front-loaded clauses: purpose first, then cost, then limits. No filler, and every clause carries information. Slightly clipped telegraphic style but nothing extraneous.

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, return values need not be described, and the description covers purpose, cost, rejection behavior and limits. The vague 'Existing source and input limits apply' is the only under-specified element; constraints like min/max items live in the schema.

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 description coverage is 67%, so the schema baseline is 3. The description contributes only indirectly ('locale-explicit' gestures at the locale enum; 'No key, credits or wallet' relates to the legacy requestId/maxPriceMicroUsd fields) and never clarifies the quantities array, id/text semantics, or the 50-item cap.

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 precise verb (normalize) and resource (locale-explicit pack-size expressions and multipacks) and names the output units (grams, millilitres, counts), plus the failure mode (reject ambiguous text). This is far more specific than a restated name, though it never names the sibling tools (commerce_pack_plan, commerce_unit_price) it must be distinguished from.

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 only implied: an agent can infer it should run this before trusting raw pack-size strings, and that ambiguous input is refused. There is no explicit when-to-use, when-not, or alternative routing vs commerce_pack_plan / agent_utilities_pack_preview. The FREE phrasing is cost guidance, not usage guidance.

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