Generate Password

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=true. The description adds family-level notes (item ids and counts only; loose dedup plans never auto-apply) that do not describe this tool's own behavior — whether the generated password is returned, stored in a cipher, or how it interacts with the vault. No tool-specific behavioral disclosure beyond the annotations.

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?

Short and front-loaded with the purpose, but a large share of the sentences are spent on sibling operations (dedup plan/apply, rotation confirm) rather than this tool. It is not padded, but the content is misallocated.

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?

An output schema exists so return values need not be explained, yet the description still fails to say what invocation does (generate and return a string? create an item?) and omits any parameter guidance for an opaque JSON blob. For a generator with polymorphic input, this leaves the agent unable to call 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% for the single params_json parameter, so the baseline is 3. However, that schema text is generic ("JSON object of parameters for the action") and the description names no accepted keys, so the agent still has no idea what to place in the blob.

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?

Opens with a specific verb+resource ("Generate password") but immediately pivots to describing the maintenance family's deduplication and rotation behavior, which belongs to the sibling tools vaultwarden_maintenance_apply_deduplication and vaultwarden_maintenance_rotate_password. An agent cannot tell from this text what generating a password actually produces or how it differs from rotate_password.

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?

No when-to-use statement for this tool. The only conditional guidance ("requires confirm: true") applies to applying deduplication or rotating a password, i.e. sibling actions, so it actively misroutes rather than helps. Nothing says when to call generate_password versus rotate_password.

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