Crop boxes per platform placement; touches no pixels

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

The readOnlyHint=true annotation is consistent with 'touches no pixels', and the description reinforces that no destructive write occurs. However it does not disclose what the endpoint returns, whether the plan is persisted, or any limits, so it adds only modest context beyond the annotations.

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?

A single tight sentence plus endpoint with zero filler and the non-destructive guarantee front-loaded. It is telegraphic rather than explanatory, but nothing is wasted.

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 no output schema, 0% parameter descriptions, and a nested body containing enums and a coordinate object, this tool needs much more than one clause. The description leaves the return shape (what a crop box looks like) and nearly all parameter semantics unaddressed.

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 description coverage is 0% and the body is nested with four undocumented fields: mode (cover/contain), focal x/y, platforms, and placements. The description explains none of these — notably the distinction between 'platforms' and 'placements' and that focal coordinates are normalized — leaving the agent to guess semantics.

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 states a concrete operation — computing crop boxes per platform placement — and adds the crucial qualifier that no pixels are modified, plus the endpoint. Combined with the title it is clearly distinguishable from creativeLibrary_resize, though it never names that sibling explicitly.

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?

'Touches no pixels' implies a dry-run/preview usage ahead of an actual resize, but the description never says when to call this instead of creativeLibrary_resize or what to do with the result. Usage is inferable rather than stated.

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