Identity register

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the write/open-world nature is covered. The description adds the important payload semantics — that a pre-hashed master password and KDF parameters must be supplied client-side rather than a plaintext password — but says nothing about authentication requirements, what happens on duplicate email, or whether registration must be completed by a follow-up call.

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?

One parenthetical sentence, front-loaded with the action and immediately followed by the key payload items. No filler or redundancy.

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 security-critical account-creation mutation with three undocumented body parameters and no output schema, the description omits the container mapping, the required/optional split, auth preconditions, and error behavior. The field list is a start but leaves the agent unable to construct a correct call.

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 0% and the three parameters (form, params, json_body) are completely opaque with no types or descriptions. The description names the logical payload fields but never maps them to form/params/json_body, so the agent still cannot tell which container holds the KDF params versus the encrypted keys.

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 ('Register') and resource ('a new account') and enumerates the credential material involved (email, name, master-password hash, encrypted keys, KDF params). It is clearly distinct from the read-oriented siblings, though it does not distinguish itself from vaultwarden_register_finish or vaultwarden_register_verification_email, which live in the same flow.

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 statement of when this endpoint should be invoked versus vaultwarden_register_finish or vaultwarden_register_verification_email, and no prerequisites (e.g. whether the server must allow open registration, whether the email must be pre-verified). The agent must infer the registration sequence entirely from tool names.

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