Ozon Consumer MCP

Overview Schema Source Related Servers Discussions Admin

ozon_return_prepare

Prepare a return for a specific purchased Ozon item without submitting it by providing the order URL, product title, quantity, and reason to get return conditions, a plan, and confirmation details.

Instructions

Подготовить возврат конкретного купленного товара/количества, НЕ отправлять. reason — точная реальная причина из формы, comment — пояснение владельца. availableChoices показывает варианты при неполной подготовке. Возвращает условия/план и confirmation при полном подтверждении.

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": {
      "orderUrl": "<orderUrl>",
      "productTitle": "<productTitle>",
      "reason": "<reason>"
    },
    "name": "ozon_return_prepare"
  }
}

Input Schema

Name	Required	Description	Default
`reason`	Yes
`comment`	No
`orderUrl`	Yes
`quantity`	No
`productTitle`	Yes
`evidenceMediaIds`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Nov 14, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Beyond annotations (which only mark a non-idempotent write), the description discloses that nothing is actually submitted, that availableChoices is returned on incomplete preparation, and that conditions/plan plus confirmation come back on full confirmation. This meaningfully clarifies the prepare-only behavior.

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?

Dense and front-loaded: purpose first, then the not-send caveat, then per-field hints and return behavior. Nearly every clause earns its place, though the Russian field-level hints are terse.

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?

No output schema exists and the return behavior is described, and the prepare/send distinction is clear. However, several of the six parameters are unexplained and there is no explicit routing to the confirmation step, leaving gaps for a 0%-coverage schema.

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 coverage is 0%, so the description must compensate. It adds real meaning for 'reason' (exact real reason from the form) and 'comment' (owner's explanation), but leaves orderUrl, productTitle, quantity and evidenceMediaIds undocumented beyond their self-evident names.

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: 'prepare a return of a specific purchased product/quantity' and explicitly scopes it with 'DO NOT send.' It distinguishes the prepare step from the confirmation step, though it does not name a sibling tool outright.

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 'not send' constraint and the mention of confirmation on full confirmation imply a two-step flow, but no explicit alternative (e.g. a confirm action) is named. Usage is inferable rather than stated when-to-use guidance.

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