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

Annotations state readOnlyHint=false, destructiveHint=false, and idempotentHint=false. The description adds crucial context: 'Calling this changes nothing: it returns a preview of what would change and a confirmation link. Only the merchant, on that page, can make it happen.' This is valuable behavioral transparency, but the word 'preview' suggests no mutation, which could be interpreted as contradicting the non-read-only annotation; however, the description clarifies that a human confirmation is needed, aligning with a non-read-only operation. This is a nuanced but acceptable disclosure.

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 concise at three sentences. It is front-loaded with the main action, then explains the preview mechanism. The sentence about money is extraneous and slightly confusing, as no price parameter exists.

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 description covers the key behavior of returning a preview and requiring merchant confirmation, which is important for understanding the tool's effect. However, it omits potential issues like authentication requirements, error handling, or what the preview contains. With no output schema, the description adequately but not fully describes the outcome.

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 100%, so parameter descriptions are already provided. The description adds a note about 'Money is integer minor units (cents)', which is irrelevant to this tool's parameters (product, url, alt), and therefore does not enhance parameter semantics beyond 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?

Clear verb+resource: 'Add a picture to a product'. Sibling tools exist for product CRUD (products_create, products_edit) but no sibling for images specifically, so differentiation is not critical. However, the description does not explicitly distinguish how the image attachment relates to those siblings.

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 explicit when-to-use or alternative guidance. The description states the method of operation but leaves it to the agent to infer that this is the only tool for adding images. There is no mention of prerequisites or conditions.

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