Skip to main content
Glama

Babelii-Diofis Customer Support

Rekomendasi produk dari Abel

find_products
Read-onlyIdempotent

Consult Babelii's product adviser: it interprets the customer's need (for example "paket data XL murah untuk 3 hari") and returns current catalogue recommendations with price, volume, validity, availability and a buy_url. Prices come only from this result. It never orders; the customer completes the purchase through buy_url. Limited per caller; use once per question, and a clarification in the result means ask the customer. An outside agent calling this tool is not Abel.

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": {
      "message": "<message>"
    },
    "name": "find_products"
  }
}

Input Schema

NameRequiredDescriptionDefault
messageYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Adds substantial behavior beyond the annotations: a per-caller rate limit, the authority constraint that "Prices come only from this result", the guarantee it never places an order, and the presence of a clarification signal in the response. None of these are recoverable from readOnlyHint/idempotentHint, so the description is carrying real weight.

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 action and result, then the constraints, with no filler sentences. The closing line "An outside agent calling this tool is not Abel" is cryptic about the persona boundary and is the one part whose value is unclear.

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?

For a one-parameter, read-only recommendation tool with an output schema present, everything an agent needs to call it correctly is covered: input intent, expected result fields, price authority, rate limit, no-order constraint, and clarification handling. Return-value structure is already in the output schema, so no gap remains.

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 covers 0% of the single 'message' parameter, so the description must compensate; it does by framing the value as the customer's need in natural language and supplying a concrete Indonesian example string. It still doesn't state length limits or whether structured fields inside the message are parsed, so it falls short of fully documenting the parameter.

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 specific verb and resource (consult the product adviser) plus the exact output it produces: catalogue recommendations with price, volume, validity, availability and a buy_url. The example query "paket data XL murah untuk 3 hari" makes the input shape concrete, and naming buy_url as the purchase path clearly separates it from order/ticket siblings.

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?

Gives explicit operating conditions: "use once per question", "Limited per caller", and "a clarification in the result means ask the customer", plus the exclusion that it never orders. It does not point to a named sibling for follow-up actions, but the buy_url redirect gives an equivalent routing instruction.

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