Take products out of a category. Money is integer minor units (cents). Calling this changes nothing: it returns a preview of what would change and a confirmation link. Only the merchant, on that page, can make it happen.
| Name | Required | Description | Default |
|---|---|---|---|
| products | Yes | The products, each by id, handle or SKU. | |
| collection | Yes | The category, by id, handle or exact title. Must be a manual one; an automatic category's rules decide what is in it. |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description states "Calling this changes nothing" and that only a separate merchant confirmation can effect the change, which asserts read-only behavior; the annotations declare readOnlyHint=false (and idempotentHint=false), asserting the opposite. This is a direct annotation contradiction, so per the rubric this scores 1 despite the otherwise useful preview/confirmation-flow detail.
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 purpose is front-loaded in the first sentence, which is good. But the second sentence, "Money is integer minor units (cents)," is irrelevant to this tool (there is no money/price parameter) and does not earn its place, cluttering an otherwise tight description.
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?
There is no output schema, and the description usefully fills that gap by explaining what the call returns — a preview of what would change plus a confirmation link — and who can act on it. That covers the essential workflow context for a two-parameter preview tool, though the readOnlyHint mismatch leaves the effect picture inconsistent.
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 parameters (products by id/handle/SKU, collection by id/handle/title and must be manual). The description adds no parameter detail and its only param-adjacent statement — "Money is integer minor units (cents)" — maps to no parameter at all, so baseline 3 applies.
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?
"Take products out of a category" is a specific verb+resource and is the clear inverse of the sibling collections_add_products, so an agent can distinguish the direction of the operation. It stops short of naming the sibling or scoping it (e.g. vs collections_edit or collections_set_rules), so it is clear but not maximally differentiating.
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?
The description implies usage and adds the important caveat that the call alone cannot complete the removal ("Only the merchant, on that page, can make it happen"), which tells the agent this is a preview step. However, it never states when to choose this versus alternatives like collections_edit or collections_set_rules, nor any prerequisite beyond what the schema already says about manual categories.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
