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

Goes well past destructiveHint=true: no undo, the image is destroyed, referencing products/categories keep a dead URL and show a broken image because the file is not detached, no reverse lookup from file to products exists, and the file may linger on the Media screen due to a separate service. This is exactly the kind of consequence detail annotations cannot convey.

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?

Front-loaded correctly: purpose, then ID source, then confirmation, then consequences. The consequence block is long and contains conversational asides ('Tell them this too'), so a few sentences could tighten, but nearly every sentence carries operational information for a destructive, irreversible call.

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 destructive one-parameter tool with no output schema, the description covers the prerequisites, the human confirmation step, the exact blast radius on referencing products, the lack of reverse lookup, and the misleading Media screen state. Nothing an agent needs before firing this call is missing.

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 the schema already says 'File id from get_media_library — not a name or a URL.' The description adds the harder imperative 'ONLY — never guess it,' which reinforces sourcing rather than restating type, but adds no format or syntax detail 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?

Opens with a specific verb and resource and an explicit scope limiter: 'Permanently delete one file from the media library.' It also distinguishes itself from the nearest confusable sibling by stating that removing a photo from one product is a product edit, not this tool.

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?

Gives explicit when/when-not: the file ID must come from get_media_library and never be guessed, the merchant must be asked to confirm naming the file, and if the caller is unsure it should send them to the Media screen instead. The alternative (product edit for unlinking a single image) is named outright.

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