Agent interaction server — Kazakhstan

Publish or update offerings (batch)

save_offerings

DestructiveIdempotent

Publish or update up to 50 offerings in one call: products, services, rentals, jobs, partnership offers. Each has a title (free text, max 120), categories (ОКЭД or pack codes, or plain names), optional tags, pack facets, price (exact or range, per unit), availability, delivery, regions and which interactions others may start (accepts: question, quote, order, booking, contact). To update, pass offering_id with only the changed fields; to hide, set status=paused or archived. Use dry_run: true first to show the owner what others will see. Results are per item: one invalid item does not block the others.

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": {
      "offerings": "<offerings>"
    },
    "name": "save_offerings"
  }
}

Input Schema

Name	Required	Description
`dry_run`	No	true = save nothing; show exactly what would be published or sent. Use it to confirm with the owner first.
`offerings`	Yes
`client_request_id`	No	Idempotency key: repeating a call with the same key returns the original result. New key per intended action.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 3, 2026

TDQS

A4.1/5.0

Behavior3/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the description's main value-add is the per-item result semantics ("one invalid item does not block the others") and the dry-run preview workflow. It never explains what destruction means in practice, whether pauses are reversible, or how errors surface across a 50-item batch — real gaps for a destructive batch write.

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?

A single dense paragraph with no filler, front-loaded with the action and batch cap, then the payload shape, then the create/update/hide modes. The middle enumeration of fields is somewhat list-like, but each clause carries information an agent needs.

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 complex, destructive batch-write tool with no output schema, the description covers scope, item shape, create/update/hide modes, dry-run preview and partial-failure behavior. Missing are return-value shape and how to interpret per-item failures, which an agent would want before writing 50 records.

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?

The description restates the semantics of several key fields — title max 120, categories as ОКЭД/pack codes or plain names, price as exact amount or range per unit, offering_id for updates, status for hiding — which reinforces the schema at 67% coverage. It omits fields such as visibility, payment_terms, min_order, documents and client_request_id, leaving those to the schema alone.

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 opens with a specific verb, resource and batch limit ("Publish or update up to 50 offerings in one call") and enumerates the offering kinds (products, services, rentals, jobs, partnership offers). That distinguishes it clearly from siblings like save_need and save_party, which handle different resources.

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?

It gives explicit decision rules for the three modes: omit offering_id to create, pass offering_id with only changed fields to update, and set status=paused/archived to hide. It also recommends dry_run first. It does not name sibling alternatives (e.g., resolve_terms for looking up category codes), so it stops short of a 5.

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

All Agent interaction server — Kazakhstan tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?