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

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=false, so safety is partly covered; the description adds genuinely new context — it is project-scoped, returns the project identity with the result, enumerates what gets recomputed, and notes the crop aim is preserved in source space. It does not, however, discuss cost, reversibility, or how repeated calls interact (non-idempotent).

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 front-loaded with the two key labels (PROJECT-SCOPED, READ/WRITE), which is good structure, and every clause carries information about what changes. It is dense and sentences are long with heavy em-dash use, but there is little outright 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 no output schema, the description carries the return burden and does so ('returns the project identity with its result'), and it explains both modes and the scope constraint for a moderately complex mutation-adjacent tool. The remaining gap is the unexplained `ratios` parameter.

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 only 33% (only project_id is documented), so the description must compensate. It explains the `apply` parameter well (apply=<ratio> rewrites to that master), but the `ratios` parameter is only gestured at via the ratio list and never mapped to the parameter, leaving its semantics ambiguous.

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 specific operation — re-solving the edit for alternate aspects (16:9, 4:3, 1:1, 4:5, 9:16) with UI scenes re-laid out, graphics/captions re-measured, and overlays re-fitted. This is a clear verb+resource that an agent can distinguish from generic add/remove tools, though it never names a specific sibling (e.g. add_aspect_shift, remove_aspect_shift, apply_format_pack) to sharpen the boundary.

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 clearly splits the two invocation modes: with no apply it lists what each master changes, and with apply=<ratio> it rewrites the edit to that master, including the sequencing hint 'export it, then the next'. That is real usage context, but it stops short of naming alternatives or stating when NOT to use this tool.

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