shopify_metafields

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

Annotations already declare destructiveHint=true and openWorldHint=true, so the mutation risk is known. The description adds the key behavioral fact that dryRun defaults to true (safe preview by default) and the 25-item cap per operation, which materially affects how an agent stages calls.

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?

One tight sentence with the mutation semantics front-loaded, followed by the read alternative and the safety default. No filler.

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 and sparse schema descriptions, the description covers the important surface: dual operations, batch limit, owner scope, dry-run default, and the read path. It omits return/auth details, but for a 4-param tool with an explicit dryRun preview this is close to sufficient.

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 only 25% (dryRun only), so the description must compensate. It adds the 25-item limit, that both set and delete accept any owner GID, and the dryRun default, but says nothing about the required namespace/key/ownerId fields or the nested item shape, leaving the bulk to the schema.

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 specific verbs (set/delete) and the resource (metafields), names the underlying GraphQL operations (metafieldsSet/metafieldsDelete), and even routes the read case to a sibling. An agent can distinguish this from shopify_get and shopify_graphql_mutation immediately.

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?

Explicitly tells the agent to read metafields via shopify_get resource metafields, which is a real alternative-tool route. It also flags the dryRun default so the agent knows the initial call is non-mutating. No exclusions for when NOT to use it against shopify_graphql_mutation, so not a 5.

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