Create backup

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

Annotations already flag destructiveHint=true, but the description goes well beyond them: it discloses this is a paid operation, that the price is product-specific, the required auth scope (services:manage) and full-access key, and the idempotency contract for lost responses. This is exactly the extra behavioral context annotations cannot carry.

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?

Purpose is front-loaded, then prerequisites, payment disclosure, retry semantics, and auth in tight sentences; every sentence carries operational weight. Slightly dense and the 'noty UUID' typo is a minor blemish, but nothing is wasted.

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, paid, multi-param mutation with no output schema, the description covers the prerequisite read path, approval gate, payment nature, idempotency handling and required permissions. An agent has everything needed to invoke it safely and correctly.

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 the schema documents each field (period, orderNo, payment, directories, idempotencyKey). The description adds meaning beyond the schema by tying period to get_backup_status options and explaining why idempotencyKey must be reused unchanged on retry, which enriches two parameters beyond their raw definitions.

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 ('Create a new backup') and immediately scopes it against siblings by naming get_backup_status as the prerequisite and disclosing the returned tracking UUID. An agent can distinguish this from get_backup_history/list_restore_points without opening any 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?

Explicit ordered workflow: call get_backup_status first for dates/price, then only proceed after the user approves the exact service/date/directories/price. It also names the retry rule and the anti-pattern (never rotate the key to retry an uncertain payment), which is exactly the when/when-not guidance an agent needs.

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