Send a password reset email to a specific user by user ID, with an optional redirect URL for the reset flow.
Send reset password email [POST /v1/users/{userId}/reset-password] Send reset password email for a specific user
| Name | Required | Description | Default |
|---|---|---|---|
| userId | Yes | The identifier of the user. | |
| x-trace-id | No | Identifier to trace group of requests. | |
| redirectUrl | No | The redirect url used for resetting password |
Changes observed during successful MCP inspections.
v1.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, idempotentHint=false, openWorldHint=true, and destructiveHint=false. The description only restates the 'send email' action and adds nothing about deliverability, whether existing passwords or sessions are invalidated, throttling on repeated calls (relevant given idempotentHint=false), or the no-op/error behavior when an email was already sent.
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?
Two sentences that say essentially the same thing, plus a bracketed endpoint path. It is short and the action is front-loaded, but the second sentence is pure redundancy rather than added information.
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?
This is an outward-facing side-effect operation (sends an email, openWorldHint=true) with no output schema and no annotations covering outcome semantics. The description never says what the caller learns on success, whether the response is always empty, or how failures like unknown userId surface — gaps an agent needs filled before invoking.
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 100%, so userId, x-trace-id, and redirectUrl are all documented in the schema. The description echoes userId via the path template ('for a specific user') but says nothing about redirectUrl — the one parameter whose behavior (where the reset link lands) genuinely benefits from extra explanation. Baseline 3 applies.
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 concrete verb and resource: send a reset password email for a specific user, reinforced by the POST endpoint path. However, it does not differentiate from close siblings such as instance_reset_password, request_recovery_codes_reset, or request_email_change, so an agent must infer which 'reset' applies here.
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?
There is no statement of when to use this versus alternatives, no prerequisites (e.g. whether the user must exist or be active), and no note on when a caller should prefer request_recovery_codes_reset or request_email_change instead. Usage is left entirely to inference from the name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.