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

Goes well past the annotations: it discloses the required scope (API key with design:write), the blast radius ('Saved designs keep their own copies, so this never breaks a design; it only frees a library slot'), and a policy preference. This tells the agent exactly what is destroyed and what is not - a mutation tool worth of trust.

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?

Four short sentences, front-loaded with the action and the id source before the caveats and preference. Every sentence carries information; slightly dense but no filler.

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?

With one parameter, no output schema, and destructive/readOnly hints already supplied, the remaining burden is auth and side effects - both covered. Only the result of a delete (success/not-found behavior) is unstated, a minor gap.

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 the baseline is 3, but the description adds provenance for the id ('from upload_image or list_uploads') and notes the upload:<id> ref form is acceptable, which is not spelled out as clearly in 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?

States a specific verb and resource with scope: 'Remove one image from the user's Uploads library by id'. It also names where ids come from (upload_image or list_uploads), which clearly separates it from delete_design, which targets a different resource.

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 a real operating rule: 'Prefer deleting images this session uploaded over ones the user added themselves', and points to the tools that produce valid ids. It does not explicitly contrast with delete_design, but the context is clear enough to route correctly.

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