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

Strong disclosure beyond the annotations: the description states the call is non-mutating ('changes nothing'), that it returns a preview plus a confirmation link, and that only the merchant can complete the change. That two-phase behavior is exactly the context annotations (readOnlyHint=false, destructiveHint=false) cannot convey. It is docked one point for the stray 'Money is integer minor units (cents)' line, which is irrelevant to a tool with no monetary parameters and adds confusion.

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?

The verb+resource leads, and the workflow explanation is tight and front-loaded. It loses a point because the 'Money is integer minor units (cents)' sentence does not earn its place in a tool with no money parameters.

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 must explain the return contract, and it does: a preview of what would change plus a confirmation link, completed only by the merchant. Combined with full schema coverage of both parameters, an agent has what it needs. A slightly fuller picture of the preview or failure modes would be needed for a 5.

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 100%, so the schema already documents both `products` (id/handle/SKU) and `collection` (id/handle/title, must be manual). The description adds no parameter-level detail, and its only numeric remark concerns money, which does not map to either parameter. Baseline 3 is correct when the schema does the work.

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 opens with a specific verb+resource: 'Put products in a category.' This is clearly distinct from the obvious siblings (collections_remove_products, collections_set_rules, collections_edit), so an agent can tell what it does without reading the schema. It stops short of explicitly naming a sibling or the scope boundary (manual vs automatic categories lives only in the schema), so it is not a full 5.

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: you call this to add products to a category, and the closing sentence implies the two-phase confirmation flow. There is no explicit 'use this instead of X' routing, no exclusion of automatic categories in the description text, and no prerequisites stated, even though collections_remove_products and collections_set_rules are obvious alternatives.

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