Skip to main content
Glama

DripRaven WhatsApp campaigns

by com.dripraven
OverviewDiscussionsAdmin

whatsapp_connect_link

Read-onlyIdempotent

Get the link the user opens to connect their WhatsApp number so broadcasts reach real phones. Two steps, because connecting registers a phone number with Meta and that number must NOT already be in use with WhatsApp: call this tool first with no arguments — it returns no link, only confirmation_question — ask the user that question and wait for their reply; then, once they confirm they have such a number, call it again with phone_number_confirmed: true to get connect_url. Returns { connect_url, connected, configured, phone_number, phone_number_confirmation_required, confirmation_question, instructions }; connect_url is null until confirmed. Connecting then requires a one-time Facebook login in the browser (a Meta requirement the agent cannot do for them) — surface connect_url to the user and ask them to finish it there. Everything after that (token exchange, number registration) is automatic. If connected is already true, the workspace is live and no action is needed.

Input Schema

NameRequiredDescriptionDefault
phone_number_confirmedNoSet to true ONLY after the user has confirmed in chat that they have a phone number they can register with WhatsApp Business — one not already in use with WhatsApp (regular app or Business) that can receive an SMS or voice call for the verification code. Omit it to get the question to ask them. Never assume the answer or set this on the user's behalf.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / phone_number_confirmed
      Added value: +{
+  "description": "Set to true ONLY after the user has confirmed in chat that they have a phone number they can register with WhatsApp Business — one not already in use with WhatsApp (regular app or Business) that can receive an SMS or voice call for the verification code. Omit it to get the question to ask them. Never assume the answer or set this on the user's behalf.",
+  "type": "boolean"
+}
  2. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Adds substantial context beyond the annotations: the first call returns no link, connect_url stays null until confirmed, and connecting requires a one-time Facebook login the agent cannot perform, while token exchange and number registration are automatic. It does not explicitly address idempotency or side effects of the confirmed call, but the safety-relevant behavior is well covered alongside readOnlyHint=true.

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-loaded with the goal, then the two-step protocol, then the return shape, then the human-in-the-loop caveat — a sensible order. It is slightly redundant, saying both 'returns no link, only confirmation_question' and 'connect_url is null until confirmed', and the full field enumeration is dense.

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?

With no output schema, the description carries the return contract itself and does so fully, listing all seven response fields and singling out connect_url semantics. It also closes the loop on what happens after the browser handoff, leaving no operational gap for the agent.

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 already 100%, so the baseline is 3, and the description earns credit above it by explaining why the flag exists (the number must not already be registered with WhatsApp), that it must be omitted on the first call, and that it must follow an actual user reply rather than an assumption.

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

Purpose4/5

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

States a specific verb and resource ('Get the link the user opens to connect their WhatsApp number') with the end goal (broadcasts reaching real phones) spelled out. The purpose is unmistakable, but it never names or contrasts itself with adjacent siblings such as connect_whatsapp, whatsapp_status, or get_subscribe_link, so an agent must infer the boundary.

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 ordered protocol: call first with no arguments to get confirmation_question, ask the user and wait, then call again with phone_number_confirmed: true. It also states the exclusion condition — if connected is already true, no action is needed — and who must do the remaining browser step.

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

All DripRaven WhatsApp campaigns 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