Skip to main content
Glama
keycrm-mcp

keycrm-mcp

by IgorShutko

stocks

Retrieve KeyCRM inventory rows, movements, inventories, warehouses, totals, and per-offer movement history with pagination and filters for stock-level analysis.

Instructions

Stock (склад): stock rows, movements, inventories, warehouses, stat, history.

Actions: list - stock rows per offer (sku, quantity, in_reserve, available, price) movements - stock movements, paginated movement - one movement by movement_id inventories - movement_id required: inventory lines of that movement warehouses - warehouses (read only here, stock writes are in crm_api) stat - totals: quantity / purchased_price / price, positive vs negative filters - filter bounds for the stock table history - offer_id required: movement history of one offer filters keys are sent as-is, e.g. {"filter[warehouse_id]": 1}.

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": "stocks"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNo
limitNo
actionNolist
searchNo
filtersNo
offer_idNo
movement_idNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

No annotations exist, so the description carries the full burden, and it does meaningful work: it discloses that warehouses is read-only here and that stock writes belong to crm_api, and that 'movements' is paginated. It stops short of stating whether all actions are read-only, how page/limit apply outside 'movements', or what happens with invalid ids.

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?

The action table is front-loaded, scannable, and every action line earns its place by naming required inputs or return fields. The opening sentence partially duplicates the action list (stock rows, movements, inventories, warehouses, stat, history), which is the only real redundancy.

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 an eight-action dispatcher with no annotations and no schema descriptions, this is close to sufficient; the return values are covered by the output schema. The remaining gap is pagination and search applicability across actions, which an agent must guess.

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?

With 0% schema coverage the description must compensate, and it largely does: it ties offer_id to 'history', movement_id to 'movement' and 'inventories', and explains that filters keys are passed through verbatim with a concrete {"filter[warehouse_id]": 1} example — non-obvious and valuable. The 'search' parameter is never mentioned, and page/limit scope is only implied by 'paginated'.

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?

Names the resource (stock/warehouse) and enumerates all eight actions with the concrete data each returns (sku, quantity, in_reserve, available, price; totals for stat). An agent can distinguish list from movements from inventories without opening the schema, and the note that writes live in crm_api separates this tool from sibling mutators.

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?

Per-action guidance is implicit but strong: 'inventories' says movement_id required, 'history' says offer_id required, and 'warehouses' explicitly redirects stock writes to crm_api. What's missing is disambiguation between overlapping read actions — when to use 'list' vs 'filters' vs 'stat' to answer a given question 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.