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

Annotations only flag idempotency and non-destructiveness; the description adds the real behavioural payload — this is an idempotent refund/compensation path, not a regeneration, and the refund trigger set is precisely bounded by HTTP status codes. The enumerated result states (reachable, unconfirmed, refund_pending, refunded) and the pointer to settlement for amounts give the agent the side effects it must anticipate.

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?

Front-loads the purpose in four characters, then layers conditions, exclusions, and outcomes in dense semicolon-delimited clauses; essentially every clause carries new information. Slightly dense for skim-reading, 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 an output schema present, return values need not be spelled out, yet the description still names the status vocabulary and where refund amounts live, so the agent knows what to expect. Combined with the explicit refund/exclusion rules, nothing material is missing for correct invocation.

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 taskId/resultId/imageIndex are already fully documented in the schema. The description only restates that the original taskId and imageIndex must be reused, adding marginal meaning (no new-generation taskId) beyond the schema's own wording.

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+resource: verify/report that the original image download failed, with the exact identifiers to supply. It is clearly distinguishable from generate/derive/upscale siblings, though it never explicitly contrasts itself with the closest neighbour, generation_status, which an agent might otherwise reach for.

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 explicit inclusion criteria (only server-issued links, only explicit 403/404/410) and an explicit exclusion list (timeouts, transient failures, normal expiry, manual deletion, local save failures do not auto-refund), plus the instruction not to submit a new generation. That is a full when/when-not contract.

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