Skip to main content
Glama

Zalo Business Reference (ZBS Template Message, OA)

Choose a Zalo channel for a task

choose_channel
Read-onlyIdempotent

Suggest which Zalo channel fits a business task, by simple published rules: ZBS template message (with the template type, tag, price and window), a free consultation reply within 48 hours of the user's last interaction (paid outside 48 hours, not allowed after 7 days), an OA broadcast to followers, or a Mini App. Tasks: otp, order_status, delivery_tracking, payment_request, appointment_reminder, customer_reply, service_rating, promotion, voucher, birthday_greeting, news_to_followers, catalog_checkout. Optional: last_interaction_hours, is_follower. Reference only. Examples: {"task":"order_status"}; {"task":"customer_reply","last_interaction_hours":30}; {"task":"promotion","is_follower":true}.

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": {
      "task": "<task>"
    },
    "name": "choose_channel"
  }
}

Input Schema

NameRequiredDescriptionDefault
taskYesWhat you need to send: otp, order_status, delivery_tracking, payment_request, appointment_reminder, customer_reply, service_rating, promotion, voucher, birthday_greeting, news_to_followers, catalog_checkout.
is_followerNoThe user follows the OA.
last_interaction_hoursNoHours since the user's last interaction with the OA (message, call, menu tap...). Decides whether a free reply is possible.

Output Schema

NameRequiredDescriptionDefault
taskYes
notesYes
disclaimerYes
affiliationYes
recommendedYes
alternativesYes
data_versionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior3/5

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

The annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is supplied structurally; 'Reference only' merely confirms it. The description does add genuinely behavioral content, namely the channel-selection rules and the 48-hour/7-day reply windows, which annotations cannot convey. It does not say what the recommendation output looks like or how confident or conditional it is, so this is a solid but not outstanding contribution beyond the structured fields.

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?

It is front-loaded with purpose and rules before the parameter hints and examples, and every sentence carries operational content. The one waste is re-listing all twelve task values in prose when the schema enum already enumerates them identically, which makes the opening sentence longer than necessary.

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

Completeness4/5

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

With an output schema present the description need not explain return values, and annotations carry the safety profile, so the remaining burden is the decision logic, which the reply-window and broadcast rules cover well. What it leaves unstated is the relationship to sibling tools (cost estimation, rule checking, template validation) for tasks that need more than a channel recommendation.

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 description coverage is 100%, so a 3 is the baseline, but the description earns a point by supplying thresholds the schema omits: the 48-hour free-reply rule and the 7-day hard cutoff for last_interaction_hours, plus the fact that is_follower governs broadcast eligibility. The three worked examples also show how to combine task with the optional parameters. Only modest added meaning remains, since the enum of tasks is restated verbatim from the schema.

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?

The description opens with a specific verb+resource+scope: 'Suggest which Zalo channel fits a business task, by simple published rules', and then names the four candidate channels (ZBS template, free consultation reply, OA broadcast, Mini App). That is far more specific than the title alone. It does not explicitly contrast itself with siblings such as check_sending_rules or estimate_message_cost, so it stops short of a 5.

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

Usage Guidelines4/5

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

'Reference only' makes clear this is advisory and does not send anything, and the reply-window rules (free within 48 hours, paid outside 48 hours, not allowed after 7 days) give the agent concrete conditions for channel selection. What is missing is explicit routing to the sibling tools that handle cost estimation or rule validation, so the alternative-selection guidance is incomplete.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.