Plan and, if a resize engine is installed, create resized variants (images only)

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

Annotations only cover readOnlyHint=false and openWorldHint=true, so the description usefully fills in the write gate, the absence of a server-side dry run, and the fact that output degrades to a request preview when confirm is omitted or no engine is installed. It stops short of what the preview looks like, what happens to existing assets when variants are created, or whether repeat calls duplicate work despite the idempotency key.

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?

Two tight sentences, front-loaded with the action and the execution condition, no filler. The parenthetical path at the end is low value to an agent but harmless.

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 4-parameter mutation with a nested object and no output schema, the description needs to carry more weight than it does. The safety story is reasonably covered, but the body parameters that determine what resize is produced are entirely undocumented, and the 'resize engine installed' condition is left unexplained.

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 50%: confirm and idempotencyKey are already documented in the schema, and the description only restates the confirm gate. The nested body is completely opaque in both places — mode's cover/contain choice, focal x/y as normalized coordinates, and how platforms vs placements differ get no explanation anywhere. That is the main semantic gap for a request-shaping tool.

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 ('create resized variants'), names the endpoint, and constrains scope to images only. The dual 'plan and, if a resize engine is installed, create' framing is a bit murky about what the tool actually returns, and the description never distinguishes it from the sibling creativeLibrary_planResize, which has an almost identical name and likely overlapping job.

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?

It gives a concrete execution gate ('not executed unless confirm: true') and an implicit read/plan precondition, so the agent knows how to run it safely. But with a sibling literally named creativeLibrary_planResize, the definition never says when to call this one versus that one, which is the central routing decision an agent faces here.

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