Skip to main content
Glama

Zoya.bg

shopping_cart

Member-only 24-hour DRAFT cart in chat, NOT the website cart. No history consent required: saves only selected product IDs/quantities for this task. Actions: select_many (items list; continues past product-specific failures and reports saved/failed/unattempted separately); active (shared cart); select (atomic absolute quantity upsert in shared cart); active_handoff (all shared items); create; view; set_item (absolute quantity, adds if missing); remove; replace (exact variant ID, keeps quantity); clear; handoff. product_name may carry the published name for bounded automatic parent recovery; never send health questions or personal data. Editing requires latest version and cart_id. Never infer IDs from SKU suffixes. Configurable line limit (default50), whole quantity1..20. For showing the basket to the user, call show_cart instead. This tool is for state checks, edits and handoff. direct_handoff is only for the confirmed Order button in the Zoya component. handoff creates a single-dispatch preview link only and does not change website cart. Once transferred, edits affect this draft only; never transfer again without warning about adding again.

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": {
      "action": "<action>"
    },
    "name": "shopping_cart"
  }
}

Input Schema

NameRequiredDescriptionDefault
itemsNo
actionYes
cart_idNo
versionNo
languageNobg
quantityNo
product_idNo
product_nameNo
remember_orderNo
parent_product_idNo
replacement_product_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does substantial work: 24-hour draft lifetime, member-only, no history consent needed, select_many's partial-failure semantics (saved/failed/unattempted reported separately), select/set_item being absolute rather than incremental, replace preserving quantity, line limit default 50 and quantity range 1..20, and handoff producing a single-dispatch preview link that does not touch the website cart. Gaps remain: it does not state what happens on a stale version/cart_id mismatch, nor what any action returns.

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?

Purpose is front-loaded, and the description is well-sized for an 11-parameter multi-action tool with no annotations. The semicolon-delimited action glossary is efficient, though a few fragments are jargon-dense ('bounded automatic parent recovery') and read as internal shorthand rather than agent-facing guidance.

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

Completeness3/5

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

For a tool this complex with zero annotations, no output schema, and 0% parameter coverage, the description covers state semantics, failure behavior, limits and the show_cart alternative well. It is still incomplete on two fronts: no indication of what active/view/handoff return (with no output schema, that burden falls here), and no per-action parameter requirements, leaving the agent to guess which of the 11 parameters each action needs.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 11 parameters, so the description must compensate and it only partly does. It effectively supplies the action vocabulary (the schema has a bare string with no enum) and explains product_name (bounded automatic parent recovery), product_id (never infer from SKU suffix), replacement_product_id (exact variant ID), quantity (absolute, 1..20), cart_id/version (latest required for edits). But language and remember_order are never mentioned, and parameters are not mapped to the actions that require them.

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 sentence names the resource precisely ('Member-only 24-hour DRAFT cart in chat, NOT the website cart') and explicitly excludes the website cart, which is the key ambiguity for this domain. The action list then enumerates the operation set, so an agent can tell this apart from show_cart and cart_history. It stops short of a single crisp verb+resource statement because the tool is a multi-action dispatcher and the description leads with the object rather than the operation.

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?

It gives an explicit alternative with the selecting condition: 'For showing the basket to the user, call show_cart instead. This tool is for state checks, edits and handoff.' It also constrains a specific action ('direct_handoff is only for the confirmed Order button') and warns against re-transferring after handoff. This is the when-to-use/when-not/alternative triad almost fully covered.

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