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

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=false. The description adds meaningful non-structured behavior: no credit charge, no provider call, and that previously delivered siblings are preserved. The stale-source guard via sourceHash is implied but not explicitly explained as a failure mode.

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, each contributing something (action, cost, integrity guard, follow-up). Slightly clipped telegraphic style, but front-loaded and waste-free.

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 non-idempotent write tool with no output schema and only 25% schema coverage, the description covers cost and preservation behavior but omits what happens on hash mismatch, whether recovery is repeatable, and what the post-recovery validation check returns.

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 only 25%, so the description must carry weight. It clarifies that crop bounds are 'original-pixel rectangles' and that sourceHash must be 'current', but says nothing about packId, batchId, or the 0-7 index semantics of the crops array.

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: cropping missing slots from a retained original PNG. The phrase 'already delivered siblings remain untouched' implicitly separates it from siblings like revise_ui_pack_png and replace_ui_component_png, though no sibling is named 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?

Gives a clear triggering condition ('after visual review' of missing slots) and a follow-up step ('Inspect validation after recovery'), plus a cost rationale (no provider call or credit charge) that affects tool choice. It stops short of naming an alternative tool to use instead when the conditions don't hold.

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