Create a new collection

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

Annotations already declare readOnlyHint=false, destructiveHint=true, openWorldHint=true, and idempotentHint=false, so the write/risk profile is covered structurally. The description adds genuinely useful non-annotation context in the rate limit (100 requests / 10 seconds per shop) with a link, but says nothing about the destructive implication, required shop scope, or the safety-gated 'confirm' flag.

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?

Two tight sentences: the operational constraint is front-loaded in italics and the capability statement follows. No filler, though the 'optional product list' phrasing is slightly imprecise given the nested payload's required offerIds.

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?

For a 7-parameter, nested-object mutation with no output schema and zero required top-level parameters, the description is thin: it omits which parameter form to choose (payload vs. flat fields vs. payload_file), the confirm-gating behavior, and any statement of what a successful call returns. The rate limit is the one piece of depth it provides.

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 71%, and the schema itself documents account, confirm, payload, payload_file, and offerIds. The description's 'name, description, and optional product list' roughly restates the schema rather than adding format, ordering, or nesting rules — notably it does not clarify that the nested payload form requires offerIds while the top-level form does not.

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 states a specific verb and resource — 'Creates a new collection' — and enumerates the fields it accepts (name, description, product list). An agent can distinguish it from update_collection and update_collection_products, but the description never names those siblings explicitly, so differentiation relies on the reader's inference.

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?

There is no guidance on when to create versus update an existing collection, no prerequisites, and no explanation of the unusual 'confirm' parameter or when it should be set. The only contextual note is a rate limit, which is a constraint rather than usage routing.

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