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

The annotations already declare readOnlyHint=false and destructiveHint=true, which the description aligns with by using 'Update'. The description adds minor behavioral context, such as the multipart requirement and the ability to upload from a local path or URL, but does not disclose side effects or implications beyond that. This is consistent with the annotation set, but the description does not significantly enhance 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?

The description is concise and to the point, with a clear subject-verb-object structure. The guidance sentence adds useful technical detail about multipart uploads without being redundant or verbose. The text is well-organized and easy to parse, avoiding unnecessary fluff.

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 simple update operation, the description provides sufficient context: the required parameters (product_id, paragraph_id, media_id) indicate the target, and the optional fields specify what can be changed. The description does not mention return values, but given the lack of an output schema and the straightforward nature of the update, this is acceptable. Overall, the essential information needed to invoke the tool correctly is present.

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?

All seven parameters are described in the schema with meaningful context. For example, 'content' specifies 'Required for EMBED', 'image_file' explains accepted formats (data URI, base64, URL) and warns against local filesystem paths, and 'focal_point' gives a format example. The descriptions are informative and help the agent understand parameter constraints, building on the 100% schema coverage.

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 the action 'Update' and the resource 'paragraph media object', which is specific. While it does not explicitly differentiate from sibling update tools, the tool name and description make the purpose unambiguous. It effectively communicates that this tool modifies existing paragraph media rather than creating or deleting it.

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 no guidance on when to choose this tool over alternatives such as shop_create_paragraph_media or shop_delete_paragraph_media. It does not mention typical use cases or conditions that would make this the appropriate choice. The guidance focuses on request format (multipart, upload source) rather than tool selection, so it falls short in this dimension.

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