Skip to main content
Glama
keycrm-mcp

keycrm-mcp

by IgorShutko

orders

List, retrieve, create, update, and delete KeyCRM orders; change statuses, add or remove products and tags, and fetch order dictionaries such as statuses, groups, sources, and totals.

Instructions

Work with orders (замовлення).

actions: list - official /order with filters + pagination (compact rows) get - full order by id (client, products, payments, shipping, tags) create - body needs source_id (+ buyer {full_name, phone/email} + products[]) update - PUT /orders/{id} with a partial body set_status - move order to status_id add_product / update_product / remove_product - product_id for last two add_tag / remove_tag - tag_id remove - delete orders by ids[] statuses / groups / totals / tags / sources - dictionaries (include_disabled=True shows hidden statuses and tags too) filters example: {"status_id": [1,2], "created_between": ["2026-10-01","2026-11-01"]}

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "orders"
  }
}

Input Schema

NameRequiredDescriptionDefault
idsNo
dataNo
pageNo
limitNo
actionNolist
tag_idNo
filtersNo
includeNo
order_idNo
status_idNo
product_idNo
include_disabledNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations, the description carries the full burden. It does add valuable non-schema behavior: create requires source_id plus a buyer block and products[], update sends a partial body to PUT /orders/{id}, remove is destructive on ids[], and include_disabled reveals otherwise hidden statuses and tags. It omits authentication/scope requirements, whether deletes are recoverable or partial, rate limits, and what distinguishes 'list' compact rows from 'get' full payload beyond a parenthetical.

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?

A single scoping sentence followed by a scannable action list, with the highest-value detail (required create payload) inlined and a concrete filters example at the end. No filler, no repetition of the schema, and the destructive action is called out plainly.

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?

For a 12-parameter multi-action dispatcher the description is a reasonable map, and the presence of an output schema relieves it of return-value explanation. It still leaves the agent to guess the parameter-to-action matrix, pagination semantics, and error/permission behavior, which matters given zero annotation coverage.

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 description coverage is 0%, so the description must compensate and largely does: it explains that ids[] drives remove, data is the create/update body with named required fields, order_id/product_id/tag_id/status_id are action-scoped identifiers, filters takes a structured object with a worked example (status_id array, created_between date range), and include_disabled toggles hidden dictionaries. Gaps remain: page, limit, and especially include are never mentioned, and the action-to-parameter binding for each action is left implicit.

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?

The description opens with a specific resource (orders) and then enumerates each action as a verb+object pair with concrete scope: list with filters and pagination, get returns the full order with client/products/payments/shipping/tags, create requires source_id + buyer + products[]. This is far more specific than a restatement of the name, though there is no explicit differentiation from siblings (the resource itself is distinct, which carries most of that weight).

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?

Action-level hints imply usage (e.g. 'remove - delete orders by ids[]', 'statuses/groups/totals - dictionaries'), so an agent can infer which action serves which intent. However, there is no explicit when-to-use/when-not-to-use framing, no stated prerequisites such as needing an order_id before update or product_id for update_product/remove_product, and the flag note about include_disabled is the only conditional guidance offered.

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