Skip to main content
Glama

Zalo Business Reference (ZBS Template Message, OA)

Check ZBS sending window, quota and promotion limits

check_sending_rules
Read-onlyIdempotent

Check whether a ZBS template send is allowed: the sending window by tag in Vietnam time (Tag 1 round the clock, Tag 2 and 3 07:00-22:00; for Tag 1 at night a warning notes the -133 wording; the conflicting announcement dates are named), the OA daily quota (levels 1000, 5000, 20000, 50000, unlimited; default 20000), Tag 3 limits per user (1 per day, 30 per month), and the quota upgrade conditions (Good quality over 7 days and 2 x the daily quota sent in 7 days). Reference only, nothing is sent. Examples: {"tag":3,"send_time":"21:30","daily_volume":15000}; {"tag":2,"send_time":"06:30"}; {"tag":3,"promo_sent_to_user_today":1}; {"tag":1,"quota_level":20000,"sent_last_7_days":45000}.

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": {
      "tag": "<tag>"
    },
    "name": "check_sending_rules"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagYesTemplate tag: 1 transaction, 2 customer care, 3 promotion.
deliveryNoHow messages are addressed: "phone" (phone number, default) or "uid" (Zalo user ID for this OA; cheaper, not for OTP, quick response, journey or carousel).
send_timeNoPlanned send time, HH:MM in Vietnam time (UTC+7).
quota_levelNoOA daily quota level for template messages: 1000, 5000, 20000, 50000, unlimited (default 20000, where a new OA starts; 1000 and 5000 are penalty levels).
daily_volumeNoTemplate messages the OA plans to send that day (all templates).
sent_last_7_daysNoMessages sent successfully in the last 7 days (to check the quota upgrade volume condition).
promo_sent_to_user_todayNoTag 3 messages this OA has already sent to the same user today (before this one).
promo_sent_to_user_this_monthNoTag 3 messages this OA has already sent to the same user this month (before this one).

Output Schema

NameRequiredDescriptionDefault
tagYes
quotaYes
windowYes
allowedYes
warningsYes
disclaimerYes
violationsYes
affiliationYes
data_versionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, so the safety profile is covered and the bar is lower. The description nonetheless adds substantial domain behavior beyond annotations: the concrete Vietnam-time windows per tag, that Tag 1 night sends carry a warning about the -133 wording and conflicting announcement dates, that 1000/5000 are penalty quota levels while 20000 is the new-OA default, and the exact upgrade conditions. It does not describe the response shape, but an output schema exists to cover that.

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

Conciseness3/5

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

The purpose is front-loaded in the first clause, which is good. But the remainder is one dense paragraph of stacked parentheticals that is hard to scan, and the trailing example JSON sits outside any labeled structure. Every fact is relevant, but the run-on packaging costs readability.

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?

For an 8-parameter domain-rule checker with full schema coverage and an output schema, the description supplies the rule content an agent needs to interpret a result: windows, quota tiers, per-user promo caps, and upgrade thresholds. The remaining gap is that the numeric thresholds are stated as prose rather than tied explicitly to which parameters trigger which check, so an agent must connect the dots itself.

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 the baseline is 3 and the schema already explains each field. The description earns above baseline by pairing parameters into meaningful combinations in its examples (tag + send_time + daily_volume; tag + promo_sent_to_user_today; tag + quota_level + sent_last_7_days), showing how the optional inputs map to the specific rule being tested. It never explains the unit or interaction of fields beyond what the schema states, which keeps it from a 5.

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: 'Check whether a ZBS template send is allowed,' then enumerates the exact rule families it evaluates (sending window, OA daily quota, Tag 3 per-user limits, upgrade conditions). An agent knows precisely what question this answers. It does not name any sibling such as validate_template or estimate_message_cost, so true sibling differentiation is left implicit rather than stated.

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

Usage Guidelines3/5

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

The phrase 'Check whether a ZBS template send is allowed' plus 'Reference only, nothing is sent' implies a pre-send verification role and makes clear this is not a send action. The four inline examples usefully sketch realistic call scenarios. However, there is no explicit when-not guidance and no alternative tool is named, so an agent must infer that validation/costing belong to the siblings.

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.