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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is known and not contradicted. However, the description adds nothing beyond that: it does not explain that arbitrary HTTP methods including DELETE can be issued, what 'target: live vs build' means, that include_pii changes data exposure, or how idempotency_key affects retries.

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?

A single short sentence with no wasted words, so there is no bloat to penalize. But the terseness comes at the cost of ambiguity — the one clause that exists does not front-load the actionable fact that this is a generic passthrough.

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 10-parameter, destructive, arbitrary-method tool with live/build targeting, PII toggling and cursor pagination, and no output schema, the description is far too thin. An agent cannot call this correctly (or safely) without details the description omits.

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 0% across 10 parameters, so the description carries the full burden and gives none of it. Nothing is said about path format, method defaulting, query encoding, target/build_id semantics, include_pii, idempotency_key, or response_cursor pagination.

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 enumerates resource domains (products, orders, refunds, returns, fulfillments, discounts, shipping, tax), which tells the agent this is a broad store-admin surface. But it lacks a verb and never states that this is a raw/arbitrary API passthrough (method+path+body), and it does not distinguish itself from typed siblings such as commerce_get, orders_get, discounts_update, or shopify_get. Purpose is inferable but vague.

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?

No when-to-use guidance is given at all. With siblings like commerce_get, orders_list, orders_update, shopify_query, and commerce_draft_apply/commerce_live_apply present, the description never says when an agent should reach for this generic escape hatch instead of a typed tool, nor any prerequisites.

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