Execute exact reviewed effects

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

Annotations already declare destructive=true, idempotent=false, openWorld=true, so the safety profile is covered; the description adds genuinely new behavior: first-failure stop, ordered execution, known/unattempted receipts, and an explicit no-retry/no-implicit-continuation guarantee. It still omits auth/scope requirements and whether already-executed tasks in the same batch are rolled back or left applied.

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 dense sentences with no filler, and the failure/no-retry guarantees are front-loaded. The extreme compression, however, borders on cryptic and costs some immediate comprehension.

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?

There is no output schema, so the description must carry return semantics, yet 'known/unattempted receipts' is never explained (format, per-task status, ordering). For a destructive, up-to-20-effect batch with no idempotency, the description should also mention auth/prerequisite context and the preview/naming relationship, which it does not.

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 75%, so the schema already documents tasks, account, and confirm. The description adds only the 'exact hash checked' constraint for review_sha256 and the 'ordered' property of tasks, but does not clarify account inheritance/credential rules or the confirm flag's interaction with review_sha256.

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 conveys the operation — submitting a batch of confirmed native effects — but never uses an explicit verb like 'execute' or 'submit', relying on the telegraphic phrase 'Confirmed ordered native effects.' It does not differentiate itself from the obvious sibling preview_commerce_batch, which is the natural counterpoint to a review_sha256-gated batch tool.

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?

The phrase 'all prevalidated before first request' implies a prior validation step (likely preview_commerce_batch) as a prerequisite, and 'confirmed' plus the schema's 'Set true only when the user asked for exactly this action' hints at the confirmation gate. However, the when-to-use versus the preview sibling and the semantics of the confirm flag are left to inference rather than stated.

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