MCP Mercado Livre

get_order_messages

Read a buyer's post-purchase message conversation for a specific order to answer delivery questions or invoice requests. Returns sender roles, message text, date, and read status.

Instructions

Read the post-sale message conversation with the buyer of a specific order. Use this to see what the buyer asked after the purchase (delivery questions, invoice requests, etc.). The pack id in the messaging API equals the order id. Returns each message with sender/recipient (user id + role, e.g. 'buyer'/'seller'), text, date (ISO 8601) and whether it was read. To reply, use send_message with the same order id.

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": {
      "order_id": "<order_id>"
    },
    "name": "get_order_messages"
  }
}

Input Schema

Name	Required	Description	Default
`limit`	No	Max messages to return, 1-50 (default 20)
`order_id`	Yes	Numeric order id from get_orders

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Oct 15, 2026

TDQS

A4.7/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the return shape (sender/recipient with ids and roles, ISO 8601 date, read status) and the domain quirk that the messaging 'pack id' equals the order id. It omits pagination behavior (the limit cap) and any auth/permission notes, so it stops short of a 5.

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?

Front-loaded with the purpose, followed by usage, return format, and the alternative action, with zero filler. Every sentence earns its place.

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?

There is no output schema, so the description's explicit enumeration of returned fields and its id-mapping note make the tool fully callable and interpretable. Purpose, usage, return values, and the sibling alternative are all covered.

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 coverage is 100%, so baseline is 3, but the description adds real meaning: it explains the messaging-API pack-id-to-order-id equivalence and reinforces the reply flow using the same id, which the schema's terse 'Numeric order id from get_orders' does not convey.

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 (Read) and resource (the post-sale message conversation with the buyer of a specific order), scoping it to one order. This clearly separates it from send_message and from get_questions, which handle other communication channels.

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?

Explicitly says when to use it ('to see what the buyer asked after the purchase') with concrete examples, and names the alternative for the opposite action ('To reply, use send_message with the same order id'). Nothing is left to inference.

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