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

It adds genuinely useful workflow context (a preview/confirmation-link design and merchant-only approval) that the annotations do not cover. However, it asserts 'Calling this changes nothing', which directly conflicts with readOnlyHint=false and idempotentHint=false, and its money-units claim conflicts with the schema's 'Price in major units'. These conflicting claims reduce trust rather than build it.

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?

It is short and the workflow point is front-loaded after an evocative opener, but the money-units sentence does not belong here (no money parameter outside rules.value, where it is contradicted) and the first sentence is cryptic rather than informative.

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 no output schema, the description correctly covers the return value (a preview of changes plus a confirmation link) and the deferred-effect model. It is nonetheless incomplete on the core action it performs and carries an internally inconsistent units claim, so an agent is left partly unsure what a successful call actually produces.

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 baseline is 3; the schema already documents kinds, sort, match, rules and their enums in detail. The description's only added parameter information is 'Money is integer minor units (cents)', which contradicts the schema's note that rules.value price is in major units, so it harms rather than helps.

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?

The description conveys the two modes poetically ('Make a category fill itself, or arrange it by hand') and maps to the smart/manual kinds, so the effect is inferable. But it never says it sets a collection's rules, and it does not differentiate itself from close siblings such as collections_edit, collections_create, or collections_add_products.

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?

It explains the confirmation flow ('Only the merchant, on that page, can make it happen') but gives no guidance on when to pick this over collections_edit or collections_create, nor any prerequisites. An agent must infer the selection context.

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