Rotate Password

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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true, so the safety profile is known. The description adds non-redundant context: results carry item ids and counts only (so the agent knows there is no rich payload to inspect), and mutation requires confirm: true. The only weakness is that it describes the whole maintenance family rather than this operation specifically.

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?

The confirm rule is reasonably front-loaded, but the deduplication sentences ('a loose deduplication plan is never applied automatically') belong to a different operation and dilute the single-tool message. Roughly half the text does not earn its place in a rotate-password definition.

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?

Annotations and the output schema mature the gaps around safety and return shape, and the description covers the confirm gate. However, for a destructive credential-rotating operation with only one opaque parameter object, not naming the target item or the generation behavior leaves an agent without enough to invoke it confidently.

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%, but the schema only documents a generic 'params_json' bag, so the description carries the burden of naming keys. It reveals that confirm must be placed inside params_json, which is genuinely useful, but says nothing about which item id to rotate or whether a new password generation is controlled by a flag.

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 title 'Rotate Password' names a specific verb and resource, but the description immediately broadens into 'Plan/apply vault deduplication and rotate or generate passwords,' so an agent cannot tell whether this tool rotates only or also plans/applies dedup. Sibling tools (vaultwarden_maintenance_plan_deduplication, vaultwarden_maintenance_apply_deduplication, vaultwarden_maintenance_generate_password) are mentioned only as an undifferentiated bundle rather than contrasted.

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?

'Applying deduplication or rotating a password requires confirm: true' is a real gating rule, and 'a loose deduplication plan is never applied automatically' is useful safety framing. But there is no guidance on when to pick rotate_password versus generate_password versus the plan_deduplication sibling, so the routing decision is left to inference.

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