Skip to main content
Glama

Babelii-Diofis Account

Cari produk

search_products
Read-onlyIdempotent

Search orderable platform products (default 10 rows, limit up to 20; a 'more' note means the page was full; one call is enough: every orderable row states price, requires_destination, needs_inquiry and open_denom as true/false). needs_inquiry=true means a bill or destination check is required first (BPJS, PDAM, PLN postpaid, e-wallet top-up; such rows often have price_type=open because the amount comes from the inquiry): prepare_purchase runs it for you. open_denom=true means the BUYER states the amount (amount parameter, min Rp1,000, for example an e-wallet top-up); the two are independent. A row with available=false and sold_out=true is a real product whose stock is empty right now: say so, never order it, it carries no ref. catalogue is a group key from the platform capability list (catalogue_groups, returned by discover_babelii), e.g. phone-credit, data-voucher, data-package, token, game, bills; omit it when unsure. A range such as 1-3 days means min_validity_days=1 and max_validity_days=3. Sort: relevance, price_asc, value_per_gb_day. For a voucher without a target number use data-voucher and requires_destination=false. Missing coverage/operator must not be guessed.

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": {
      "query": "<query>"
    },
    "name": "search_products"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNorelevance
limitNo
queryYes
operatorNo
catalogueNo
max_priceNo
max_volume_gbNo
min_volume_gbNo
max_validity_daysNo
min_validity_daysNo
requires_destinationNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description layers on real behavior: default 10 rows with a limit cap of 20, the 'more' marker meaning a full page, and what each returned flag (needs_inquiry, open_denom, available/sold_out) implies. The sold_out instruction ('say so, never order it, it carries no ref') is exactly the kind of consequence disclosure annotations cannot express.

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?

One dense run-on paragraph with no line breaks or grouping, making the flag semantics hard to scan at a glance. Content mostly earns its place, but the e-wallet top-up example is repeated across the needs_inquiry and open_denom explanations and the inline catalogue example list is expendable.

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 11-parameter tool with 0% schema coverage and an output schema, the description covers pagination, filter mappings, category selection and result interpretation well. The 'operator' parameter's expected format is never stated beyond the caution not to guess it, which is a noticeable hole for a search filter.

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 0% across 11 params, so the description must compensate and largely does: it defines sort values (relevance, price_asc, value_per_gb_day), the limit default/cap, catalogue as a group key from catalogue_groups, and the min/max_validity_days mapping from a '1-3 days' range. It leaves max_price, min_volume_gb and max_volume_gb entirely to name inference, and never states currency for max_price.

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 opening clause gives a specific verb and scoped resource: 'Search orderable platform products', plus the domain (platform, orderable) that separates it from a generic product lookup. It never names the closest sibling (search_marketplace), so the agent must infer which search to use, which keeps it below 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?

Explicit operational guidance is present: 'one call is enough', 'omit it when unsure' for catalogue, use data-voucher with requires_destination=false for vouchers without a target number, 'Missing coverage/operator must not be guessed', and it routes inquiry flows to prepare_purchase. There is no statement of when to prefer search_marketplace or get_product instead, which is the remaining gap.

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.

Resources