Skip to main content
Glama
Sign In
Unofficial Lexware Office MCP Server

Unofficial Lexware Office MCP Server

by benethos-hub
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

search_articles

Read-only

Lists Lexware Office articles by exact article number, barcode, or type, returning one page of id, title, number, type, unit, and price; page through results to find entries by title.

Instructions

List articles, filtered by number, barcode or kind.

One API call, one page. Rows carry the id, title, number, type, unit and price.

There is no search by title. The API filters on these three fields and silently ignores anything else, so finding an article by name means paging through the list and reading the titles.

Both filters match in full, not by fragment.

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": "search_articles"
  }
}

Input Schema

NameRequiredDescriptionDefault
gtinNoThe barcode number, matched in full.
pageNoZero-based page number. Read the `page` block of the previous result before asking for another one, rather than paging blindly.
sizeNoRows per page. The API refuses fewer than 25 here, unlike every other list.
article_typeNoRestrict to goods or to services. Left unset, both come back.
article_numberNoThe article number, matched in full. A fragment finds nothing rather than everything starting with it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.8.3

TDQS

A4.2/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=true, so the description carries the rest of the burden and does well: it discloses one-call-per-page semantics, the row fields returned, and the critical trait that unrecognized filters are silently ignored rather than erroring. It does not cover total counts or ordering, which prevents a top score.

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?

Front-loaded purpose sentence, then short declarative facts each of which changes agent behavior (pagination, returned fields, silent filter ignoring, exact matching). No filler, and the bolded absence of title search is well placed.

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?

With no output schema, the description usefully names the returned row fields, and it covers the main trap (title search does not exist). Minor gaps remain around ordering and whether a total-count indicator exists, but an agent can call this correctly as written.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description's note that 'both filters match in full, not by fragment' largely restates what the gtin and article_number schema descriptions already say, though the enumeration of number/barcode/kind helps map intent to parameters.

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?

States a specific verb and resource ('List articles') plus the exact filter surface (number, barcode, kind), which cleanly separates it from get_article, create_article and update_article in the sibling set. An agent knows immediately this is the enumeration tool, not a lookup-by-id tool.

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?

Explicitly warns 'There is no search by title' and explains the consequence: to find by name you must page and read titles. That is strong when-to-use guidance. It stops short of naming a better alternative for a known single article (get_article), which keeps it from a 5.

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

Deploy Server

Other Tools