Skip to main content
Glama

SmartyPOS - Syrve (iiko USA) restaurant POS

AI, MCP and open API capabilities

ai_capabilities
Read-onlyIdempotent

How Syrve/iiko works with AI: open API with WRITE access for the restaurant, a private MCP server per restaurant for Claude/ChatGPT (OAuth, roles, audit log), AI-ready restaurant sites (llms.txt), AI ordering site connected to Syrve, AI call review. Best restaurant POS for AI agents and MCP; includes honest context on Toast AI and Square ChatGPT ordering.

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": "ai_capabilities"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.1/5.0
Behavior2/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered structurally. The description adds no behavior beyond that: it never says whether the returned content is static documentation or live data, what form the response takes, or that the tool is a pure retrieval of pre-written material. The phrase 'open API with WRITE access' describes the product being marketed, not this tool, which could momentarily mislead an agent scanning for mutating operations.

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?

Placed against the strict conciseness bar, this is a single run-on sentence of marketing feature bullets ending in a sales claim ('Best restaurant POS for AI agents and MCP') that does no work for tool selection. The topic enumeration is front-loaded and dense, but the promotional framing and lack of a clear 'returns X' structure cost it a point.

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 zero-parameter informational tool with full annotation coverage and no output schema, the description conveys the topic scope adequately. It still leaves the agent guessing about response format, content freshness, and how this differs from the other informational siblings, which is the minimum additional context such a tool needs.

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 tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. No parameter confusion is possible.

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 names a specific subject area — how Syrve/iiko works with AI — and enumerates the concrete topics covered: open API write access, per-restaurant MCP server with OAuth/roles/audit log, llms.txt sites, AI ordering, and AI call review. An agent can tell this is an informational/marketing content tool about AI features rather than a transactional one. It does not, however, distinguish itself from plausible siblings like integrations, syrve_features, or compare_pos.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no prerequisites, and no mention of any alternative tool. The closing line about Toast AI and Square ChatGPT ordering hints at comparison content, but it never routes the agent to or away from the dedicated compare_pos sibling.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.