Skip to main content
Glama

Proof Holdings

by holdings.proof
OverviewDiscussionsAdmin

create_account

Create an account-bootstrap session for agent-driven onboarding. Public endpoint (no API key required). Returns a session id, channel-specific instructions, and — FOR TELEGRAM AND WHATSAPP ONLY — deep_link, qr_code (base64 PNG) and qr_text (UTF-8 text QR).

The endpoint is safe to call regardless of whether the submitted identity is new: completing verification transparently creates a User when none exists, or logs the user in when one already does. The response is intentionally uniform — the server does NOT reveal whether the identity is already registered (this would be a user-enumeration oracle). If the agent needs to distinguish new-vs-returning users, call get_current_user after verification and inspect the user's created_at.

EMAIL CHANNEL SENDS NOTHING HERE. The response carries email_sent=false and send_required=true: confirm with the user that the address is theirs, then call send_account_email. The other channels dispatch nothing either way — the user sends the first message themselves (reverse OTP).

Agent usage: (1) Call create_account with the user's chosen channel. (2) For email, confirm with the user and call send_account_email. On telegram/whatsapp pass deep_link to render_auth_link, which returns the clickable link with a QR code beneath it to you. On sms deep_link is an EMPTY STRING and render_auth_link will reject it — show sms_message, which is what the user sends; this response carries no destination number, so do not invent one. Do not hand qr_text to a link renderer either — it is the link already rendered as QR art; print it verbatim inside a fenced code block if a real terminal needs the QR. (3) Once your reply shows the user the challenge, call wait_for_account_creation with the session id until verification completes. (4) On verified, JWT + refresh cookies are set; proceed with whatever follow-up the agent was asked to do.

The user does not see tool results — most clients fold them away, render_auth_link's output included. Before you wait or poll, put what the user must act on into your own reply text: the link itself (not a sentence announcing it), the SMS text and number, or a note to check their inbox.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
emailNoEmail address. Required for email channel.
channelYesAuthentication channel the user will verify through
phone_numberNoE.164 phone number. Required for SMS channel (determines DID routing).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare readOnlyHint=false and destructiveHint=false, but the description adds substantial context: public/no-API-key access, a deliberately uniform response that avoids a user-enumeration oracle, email channel sending nothing with email_sent=false/send_required=true, and JWT+refresh cookies being set on verified. This is far beyond what the annotations convey.

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?

Purpose, response shape and the numbered agent workflow are front-loaded and well structured, and most sentences carry operational value. It is long and dense for a single tool, but the length is largely justified by the multi-step orchestration it must document.

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 enumerates return fields (session id, channel instructions, deep_link, qr_code, qr_text, email_sent, send_required, sms_message) and explains the JWT/cookie outcome on verification. Combined with the full usage flow, an agent has everything needed to call and follow up correctly.

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

Parameters4/5

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

Schema coverage is 100%, so the schema already documents channel, email and phone_number, giving a baseline of 3. The description adds real meaning tied to the channel parameter — deep_link is populated only for telegram/whatsapp, empty for sms, and phone routing behavior — which helps the agent choose and interpret inputs.

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 precise verb+resource ('Create an account-bootstrap session for agent-driven onboarding') and immediately scopes it against siblings by naming send_account_email, render_auth_link and wait_for_account_creation as the follow-on calls. An agent can tell exactly what this does versus start_login, create_session or create_identity_challenge without opening any schema.

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?

Provides an explicit numbered when-to-use workflow, including channel-specific routing (email → send_account_email, telegram/whatsapp → render_auth_link, sms → show sms_message), plus 'when-not' warnings (do not hand qr_text to a link renderer, do not invent an SMS number, render_auth_link will reject empty deep_link). Nothing about the decision path 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.

All Proof Holdings toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources