Export bounded private metadata

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

Annotations already declare destructiveHint=true, openWorldHint=true, non-idempotent and non-readOnly. On top of that the description adds real behavioral context: writes a new file with mode 0600, enforces page/item/byte budgets, supports explicit continuation, follows no URLs, and is not an atomic backup (so partial output is possible). That is meaningful beyond the annotations, though the byte budget and 'exclusive0600' phrasing are cryptic.

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?

It is a single front-loaded sentence with no filler, which is good. But it is dense with unglossed jargon ('exclusive0600', 'page/item/byte budgets', 'no atomic backup') that hurts parseability, and the trailing exclusion list is hard to map to concrete behavior.

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 destructive, 8-parameter tool with nested arguments, low schema coverage, and no output schema, the description leaves gaps: it does not say what the exported file contains per operation, how errors/partial writes should be handled, or how account/arguments interact. Adequate as a minimum-viable sketch but not complete.

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 low (38%) across 8 parameters, so the description must compensate. It clarifies budgets (page/item) and continuation semantics, but says nothing about account, arguments, start_offset, or confirm beyond the schema's own terse hints. Partial compensation only.

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 names a specific verb (export), the payload format (cursor-based JSON), and the output target (a new private file), so the core action is identifiable. However, it never says which resources are exported (the operation enum lists products/sales/subscribers/payouts), and it does nothing to distinguish this bounded export from the many sibling list_* tools.

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?

There is no explicit when-to-use guidance or named alternative. 'Confirmed' and the confirm parameter imply a user-approval precondition, but the description never states when this export should be chosen over, e.g., list_sales or list_products directly. Usage context is only weakly implied.

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