create_product

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

No annotations are provided, so the description carries the full transparency burden. It does disclose meaningful behavioral details: variant prices use major currency units, images should be public URLs, and status controls visibility. However, it doesn't mention defaults beyond 'draft' status, what happens on creation (e.g., whether handle auto-generation is the only auto behavior), or potential side effects. Given multiple behavioral disclosures, 3 is appropriate.

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 description is a single paragraph, reasonably compact for the complexity it covers. It front-loads the core action and then provides key operational details plus a concrete example variant. It's somewhat dense with commas and chained clauses, but every sentence adds meaningful guidance. A slightly more structured format could help, but it's efficient for 20 parameters.

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 20-parameter creation tool with low schema coverage and no annotations or output schema, the description does a solid job explaining the most complex and error-prone aspects: variant/option relationships, currency formatting, and status semantics. The concrete example variant bridges the gap on complex nested structures. Gaps remain for several parameters (type_id, material, category_ids semantics), and there's no explanation of return behavior, but the description handles the core complexity well.

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 only 45%, so the description must compensate for undocumented parameters. It adds substantial value: explains the variant structure with a full JSON example, clarifies currency unit format, and explains that images are public URLs. However, 20 parameters exist and 11 have no schema description, leaving several (type_id, material, subtitle, weight, discountable, collection_id, etc.) unexplained in both schema and description. The description covers the most critical creation parameters well.

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 clearly states 'Create a product' with a specific verb and resource, and elaborates on key creation aspects (options, variants, status, images). It doesn't explicitly differentiate from siblings like create_variant (which is for adding variants to existing products) or update_product, but the creation-focused purpose is clear and distinct enough given the verb.

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?

The description provides usage context by explaining key workflows: how to structure options/variants, how to set publish status ('draft' vs 'published'), and how to pass images. It explains the variant structure with a concrete example. However, it doesn't explicitly state when to use this vs alternatives like create_variant or update_product, nor does it mention prerequisites like needing type_id or category_ids.

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