Skip to main content
Glama

Autoload: save profile

autoload_create_or_update_profile_v2
Destructive

Create or update an autoload profile for Avito with multiple feeds, schedule, and email reports. Overwrites existing settings or creates a new profile.

Instructions

Creates or updates (upsert) an autoload profile (v2, current version). Overwrites the existing profile settings on the Avito side; if no profile exists, it creates one. Supports multiple feeds via feeds_data (unlike v1 with a single upload_url) — prefer this method. The uploads themselves run on the schedule, or manually via autoload_upload.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
autoload_enabledYesAutoload status: true — enabled, false — disabled. Required.
report_emailYesEmail address to which Avito will send upload reports. Required.
feeds_dataYesArray of feeds (at least one). Each element = {feed_name: feed name for the report, feed_url: URL of the file with listings, starts with http/https}. Required. See the FeedsData schema in swagger autoload.json.
scheduleYesSchedule of regular uploads (array of periods): each element = {rate: number of listings per period, weekdays: [0-6, where 0=Monday], time_slots: [0-23, where 0 = the 00:00-01:00 interval]}. Moscow time. Required. See the ExportSchedule schema in swagger autoload.json.
agreementNoAcceptance of the Avito Autoload terms of use. Required only when first creating a profile; can be omitted on update.
dryRunNov0.7.0: if true — returns a preview of the HTTP request without calling the Avito API. Safe for inspecting exactly what would be done. Default: the value of AVITO_MCP_DRY_RUN_DEFAULT (usually false).
idempotencyKeyNov0.7.0: optional key for duplicate protection. A repeat call with the same key within AVITO_MCP_IDEMPOTENCY_TTL_SEC returns the cached result. The same key with different args returns a conflict error — this is safe by design.
Behavior4/5

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

The description discloses the destructive nature (overwrites settings), upsert behavior, and safety via dryRun parameter. Annotations (destructiveHint, idempotentHint) are consistent. However, it is ambiguous whether the operation is a full replacement or partial update.

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 description is three sentences with no extraneous information. It front-loads the core purpose, then adds behavioral distinctions and sibling tool references, all efficiently.

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?

Given the complexity (7 params, nested objects, no output schema), the description covers behavior and distinctions, but lacks information about the response format. The rule allowing omission of return values only applies when output schema exists, which is not the case here.

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% with detailed descriptions. The description adds context by explaining the advantage of feeds_data over v1 and the purpose of dryRun and idempotencyKey, though it largely relies on schema for details.

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 clearly states the verb ('creates or updates'), the resource ('autoload profile v2'), and explicitly distinguishes it from v1 by highlighting support for multiple feeds. The title and name also reinforce the purpose.

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?

The description advises preferring v2 over v1 and references autoload_upload for manual uploads. However, it does not explicitly state when not to use this tool or list prerequisites like terms acceptance, though the agreement parameter is mentioned.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/elchin92/avito-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server