Export bounded private metadata

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

With annotations already declaring destructiveHint=true and readOnlyHint=false, the description still adds real behavioral context: file mode 0600, page/item/5MiB budget caps, explicit page/offset continuation, and negative guarantees (no links followed, no binary downloads, no atomic-backup guarantee). This meaningfully exceeds the annotation surface, though it doesn't explain what the destructive aspect actually destroys.

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?

A single compact sentence, front-loaded with the export action and file target before the budget and continuation clauses. It wastes no words, though the heavy abbreviated jargon slightly impairs readability.

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 an 8-parameter tool with nested objects, 38% schema coverage, and no output schema, the description gives good behavioral context but omits guidance on operation selection and the confirm/account semantics. It is adequate but not sufficient on its own.

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 38%, so the description must compensate, and it does partially by explaining page/size budgets and offset-based continuation. However it says nothing about the operation enum values, account, confirm, or the nested arguments object, leaving much of the 8-parameter surface undocumented.

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 verb (export) and resource (native page/size/results metadata) written into a new file, which is clearly distinguishable from the many sibling list_* tools that return data inline. It is dense with jargon but the core action and output target are identifiable without opening the schema.

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 guidance on when to choose this export tool over the sibling list_products/list_orders/etc. tools it wraps, nor any statement of prerequisites beyond the implied 'Confirmed' in the name. The agent must infer that this is the file-producing variant.

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