Skip to main content
Glama
@cmssy/mcp-server

@cmssy/mcp-server

Official

Send customer password reset

send_customer_password_reset
Destructive

Issue a one-hour password reset token for an active customer who cannot sign in, delivering it through the workspace webhook and, when enabled, email.

Instructions

Issue a password reset token, the same one the site's forgot-password flow issues, and send it as the webhook event account.password_reset_requested to the workspace's webhooks; when the customer's model has account emails on (get_model auth.email.enabled), cmssy also emails the customer itself. The token works for one hour. For an active customer who cannot sign in. Refused for a suspended customer, for one who has not verified yet (use resend_customer_verification), for a customer whose account model has no password sign-in, and after five account requests for the same customer in an hour. emailDelivery.status is cmssy's own email: SENT (handed to the email provider), FAILED (not sent - error says why, the email log lists it) or OFF (the model leaves emailing to the app). endpointSubscribed: false means no enabled webhook endpoint receives the event; with emailDelivery OFF nothing then reaches the customer.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "id": "<id>"
    },
    "name": "send_customer_password_reset"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesThe customer's id (from list_customers)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.73.2

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only say it is a mutation (readOnlyHint=false, destructiveHint=true); the description goes far beyond by disclosing the one-hour token lifetime, the exact webhook event emitted, the rate limit of five per hour, and what happens for each refusal case. It also explains the two response fields (emailDelivery.status values SENT/FAILED/OFF and endpointSubscribed) that determine whether the customer actually receives anything.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the action and delivery mechanism before the eligibility rules and response semantics, and nearly every clause carries operational information. The middle sentence is dense and stacks four refusal conditions in one breath, which slightly hurts scannability but does not waste words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, yet the description documents the meaningful return signals (emailDelivery.status values and their meanings, error, endpointSubscribed) and the side effects an agent must expect. For a single-parameter, side-effecting tool with rate limits and multiple failure modes, nothing an agent needs before calling is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the single `id` parameter is already documented in the schema as the customer id from list_customers, so the description adds no new meaning about the parameter itself. Baseline 3 applies since the schema carries the parameter burden.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: issue a password reset token identical to the site's forgot-password flow and deliver it as the account.password_reset_requested webhook event, with optional direct email. It is clearly distinguishable from resend_customer_verification, which is named as the correct tool for unverified customers.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit positive condition ('For an active customer who cannot sign in') and four explicit refusals — suspended customer, unverified customer (with the alternative tool named), no password sign-in on the model, and more than five requests per customer per hour. An agent can decide eligibility without guessing.

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

Deploy Server

Other Tools