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

Annotations already indicate readOnlyHint=false and destructiveHint=false, so the description adds little about side effects or permissions. It repeats 'create' but does not disclose any additional behavioral traits. The description also contains a misleading statement about passing a 'local path' while the schema explicitly prohibits filesystem paths, which could mislead the agent.

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 not well-structured: it repeats the guidance sentence, is truncated mid-sentence ('EMBED: pass...'), and includes an awkward 'context: product_id, paragraph_id' suffix. It could be condensed into a single clear sentence without repetition.

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 create operation with no output schema, the description does not mention return values, error handling, or any prerequisites. It does not address the fact that required parameters depend on media_type, which is partially covered by the schema but not fully explained. The truncated sentence and local-path contradiction further undermine completeness.

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% and already documents each parameter's purpose and constraints. The description's parameter guidance is redundant with the schema. More critically, the description contradicts the schema by suggesting a local filesystem path is acceptable for image_file, while the schema explicitly states 'Do NOT pass a local filesystem path.' This confusion reduces the value of the description.

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 tool creates a media object for a paragraph, and specifies two media types (PHOTO and EMBED). It is distinct from sibling create_*_paragraph tools because it focuses on media attachment. However, the description is slightly redundant and includes a confusing appended context note, which prevents a perfect score.

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 guidance for the two media types, telling which parameters to pass for each. It does not explicitly compare with alternatives like shop_update_paragraph_media or shop_create_paragraph, so an agent may not know when to choose this over similar tools. The guidance is implied but not explicit about exclusions.

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