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

Annotations declare the basic profile (not read-only, destructive, not idempotent), but the description adds substantial behavioral context: the draft-only constraint, the approval-gated publishing flow, and a detailed sensitive-tier approval protocol (from-now-on vs just-once approvals, 'call it on the first clear ask; the card is the yes'). This goes well beyond what annotations convey. No contradiction with annotations is present.

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 first sentence is excellent — dense and front-loaded with the core facts. But the 'Routing: Shopify: create a DRAFT product (title/description/tags) — never live' line largely repeats the first paragraph, and the approval bracket is jargon-heavy ('the card is the yes — do not re-ask in chat'). Sections are clearly delineated, but the redundancy and verbosity keep it below a 4.

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 6-param tool with no output schema and minimal annotations, the description covers the essential ground: what it does, the draft-vs-live constraint, when to invoke it, and the approval mechanics. Minor gaps remain — the return value on success (e.g., product ID) is unspecified and prerequisites such as an active Shopify connection are unstated — but the description is considerably more complete than the typical definition.

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 every parameter is already documented in the schema, establishing the baseline of 3. The description adds marginal grouping value by mapping 'Sets title, description, vendor, type, and tags' onto the schema parameters, but it does not deepen parameter-level semantics — no format details, no constraints, no interplay with companyId.

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 specific verb and resource — 'Create a new product in the connected Shopify store' — and adds the critical distinguishing qualifier: the result is always a DRAFT and never live. This differentiates it from siblings like publish_shopify_product, update_shopify_product_draft, and update_live_shopify_product without needing to open their schemas. It also enumerates the fields it sets (title, description, vendor, type, tags), so an agent knows exactly the scope of the call.

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?

Gives clear usage context: 'Use when building out the catalog; the operator approves go-live later.' The 'never live — publishing to buyers is a separate approval-gated step' phrasing tells the agent this is not the go-live path and implies a publish tool exists. However, it never names that sibling alternative explicitly (publish_shopify_product) nor states when-not-to-use conditions, so it falls short of the explicit-alternatives bar.

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