Skip to main content
Glama
keycrm-mcp

keycrm-mcp

by IgorShutko

documents

List, preview, print and attach KeyCRM document templates for orders, leads and clients, and export xlsx templates and print layouts.

Instructions

Printed documents (документи): templates, preview, print.

Actions: list - document templates of the account (empty on this tenant) by_scope - scope required (order / lead / client), templates for it export_template / export_formats - xlsx export template and formats print_layouts - list printing layouts (config/print) preview - data required: {"type": "order", "structure": }; structure may be a dict/list and is stringified for you; returns rendered HTML view preview_pdf- same body, returns a short text head of the PDF (the client truncates binary bodies) print - template_id + scope + model_id, returns document text head attach - template_id + scope + model_id + data, attaches a document Document writes are limited to preview/print/attach; templates are not created or edited here.

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": "documents"
  }
}

Input Schema

NameRequiredDescriptionDefault
dataNo
scopeNo
actionNolist
model_idNo
template_idNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
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 delivers real behavioral detail beyond the schema: 'list' is empty on this tenant, structure arguments are stringified automatically, preview returns rendered HTML, and both preview_pdf and print return only a short text head because the client truncates binary bodies. These are exactly the gotchas an agent needs. It does not disclose permission requirements or whether 'attach' is idempotent or reversible, which is the main remaining gap for a tool that performs writes.

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 one-line purpose followed by an aligned action list is well front-loaded and scannable; each line carries a distinct fact rather than restating the name. The multi-line wrapping of the preview entry is slightly awkward but the content in it earns its place by warning about output truncation.

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 five-parameter, multi-action tool with no annotations and an output schema, the description covers what each action needs, what several of them return, and what the tool cannot do. The remaining holes are the semantics of model_id and the side effects or repeat-call behavior of attach, which matter for a tool that mutates documents.

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 it largely does: it defines the action vocabulary, the allowed scope values (order / lead / client), the shape of 'data' (a JSON structure that may be a dict or list and is stringified), and shows template_id and model_id in combination for print/attach. The weak point is 'model_id', whose meaning (presumably the underlying order/lead/client record) is never explained, and no parameter types are stated.

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?

Opens with a concrete resource statement ('Printed documents: templates, preview, print') and then enumerates every action with its own verb and object, so an agent can tell 'preview' from 'print' from 'attach' without opening the schema. It is a multi-action dispatcher rather than a single-purpose tool, which slightly blurs the headline purpose, but each action line is specific.

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?

Gives per-action selection conditions in the form of required inputs ('by_scope - scope required', 'preview - data required', 'print - template_id + scope + model_id'), which is exactly the routing information needed to pick an action. It also states a negative boundary: 'Document writes are limited to preview/print/attach; templates are not created or edited here.' What it lacks is guidance on when to reach for this tool versus domain siblings like orders or files, so it stops short of explicit alternatives.

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