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

Beyond the annotations, it discloses lifecycle behavior that matters a lot: the product is hidden inside the draft, is discarded with the draft, and only becomes live on publish. That prevents the agent from treating this as a customer-visible write. It does not mention that the call is non-idempotent (retries can create duplicates, matching idempotentHint=false) or what validation failures look like, so it falls short of full transparency.

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 sentences, both earning their place: the first defines the operation and payload, the second covers lifecycle and the consent precondition. Front-loaded and free of restatement of the title or schema.

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?

The tool has a deep nested schema, no output schema, and creates a durable resource, so the description should say what handles come back (product id, draft ref) for follow-up edits. That return-value gap and the absent duplicate-on-retry warning leave it only partly complete for a mutation of this complexity.

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 coverage is 67% and the nested product object is heavily self-documented (options max 3, variant option ordering, price as a decimal string, file GIDs). The description's 'with options, variants, prices and media' merely names those families, adding little syntax or constraint detail beyond the schema. Baseline 3 is appropriate.

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 ('Create') and resource ('a new hidden product in a Fudge draft') and enumerates the payload it can carry: options, variants, prices, media. The resource noun 'product' cleanly separates it from the create_draft_article / create_draft_collection / create_draft_page siblings without needing their schemas.

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?

'Use only when the merchant asks' gives a consent-based precondition, which is real guidance about when not to call it. However, nothing tells the agent how to choose this over adjacent draft-authoring tools (e.g. edit_draft_content for products that already exist) or what to do when no draft exists yet (start_draft), so the routing is only partially resolved.

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