Export bounded private metadata

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

Annotations declare destructiveHint=true, readOnlyHint=false, openWorldHint=true, idempotentHint=false, so the safety profile is largely covered. The description adds meaningful context: creates a new exclusive 0600 file, enforces page/item/5MiB budgets, supports explicit continuation, does not follow signed links or download binaries, and is not an atomic backup. These are valuable beyond annotations, though file permissions after failure and partial-write behavior are not fully clarified.

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?

Very compact: two sentences front-load the core action and constraints. Every clause carries information, though 'per/per_page' and 'exclusive0600' are compressed to the point of obscurity for an agent unfamiliar with the API.

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, non-idempotent, open-world export tool with 8 params at 38% schema coverage and no output schema, the description covers budgets, continuation, file permissions, and limits building. But it omits operation enum semantics, confirm behavior, output_file expectations, and what happens to partial exports—gaps an agent needs to invoke it safely.

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 only 38% across 8 params, so description must compensate. It mentions page/item/5MiB budgets and continuation, which aligns with max_pages/max_items/start_offset but does not name them. It does not explain operation enum variants, output_file format, account label semantics, confirm usage, or the nested arguments object. Marginal compensation for a notable coverage gap.

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 clear verb and resource: exporting metadata into a new exclusive file, with pagination and budgets. It distinguishes itself from sibling read tools by noting it writes a file and has budgets/continuation. However, 'per/per_page' and 'native page' phrasing is cryptic and not standard terminology, leaving the exact operation somewhat ambiguous.

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 description implies this is for bounded exports rather than ad-hoc reads, and warns it is 'not an atomic backup' and that signed links are not followed. But it does not explicitly say when to use export_resources instead of the many list_* siblings, nor does it state required confirm semantics in the guidance.

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