Skip to main content
Glama
Ozon Consumer MCP

Ozon Consumer MCP

by errogaht

ozon_action_confirm

Destructive

Confirm a final Ozon purchase, refund/discount, or review submission using the preview token/digest and confirmed=true. Executes once after rechecking facts; do not retry on unknown status.

Instructions

ОПАСНОЕ КОНЕЧНОЕ ДЕЙСТВИЕ: оформить покупку, отправить скидку/возврат или опубликовать отзыв. Только по ЯВНОМУ поручению владельца после чтения preview. Передать точный token/digest и confirmed=true. Повторно проверяет факты; одноразовое выполнение. Нельзя использовать для тестов разработки. При unknown НЕ повторять.

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": {
      "confirmation": "<confirmation>"
    },
    "name": "ozon_action_confirm"
  }
}

Input Schema

NameRequiredDescriptionDefault
confirmationYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.8/5.0
Behavior5/5

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

Beyond annotations, it discloses that facts are re-verified at execution time, that execution is one-shot, that an owner-level authorization is required, and that unknown outcomes must not be retried — exactly the operational context an agent needs around a destructive call. This is consistent with destructiveHint=true and idempotentHint=false and adds real value on top of them.

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

Conciseness5/5

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

The danger warning is front-loaded, and each following sentence adds a distinct constraint (authorization, exact credentials, re-verification, one-shot, no dev testing, no retry on unknown). No filler.

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 a destructive, non-idempotent, open-world tool with a nested confirmation object and no output schema, the definition covers authorization, prerequisites, retry policy, and test exclusions. It could go one step further and point at ozon_action_status for resolving an unknown outcome instead of merely forbidding retries.

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?

With 0% schema description coverage, the description does meaningful work: it states that the exact token and digest obtained from the preview must be passed and that confirmed=true is required, which links the opaque strings to their source. It still doesn't explain what the digest protects against or what error a mismatched pair produces.

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?

The description names concrete verbs and outcomes (make a purchase, send a discount/return, publish a review) and frames the tool as the final confirmation step that follows a preview, which separates it from the prepare/checkout siblings without ambiguity. An agent can tell this is the terminal commit call for several flows.

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 explicit when-to-use conditions (only on the owner's EXPLICIT instruction, only after reading the preview) and explicit when-not (never for development tests, never retry on unknown). The alternative path is implied clearly: read the preview first, then call this.

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