betrieb_ueberblickNennt die aktuellen Eckdaten: wie viele Aufträge offen und wie viele terminiert sind, wie viele Rechnungen unbezahlt und davon überfällig, und die Summe der offenen Posten. Guter erster Aufruf, um zu verstehen, worum es gerade geht.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds behavioral context by enumerating the specific metrics returned (counts, sums), which helps set expectations. It does not contradict annotations and provides value beyond the structured hints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences long and efficiently front-loads the key metrics in the first sentence, with a usage recommendation in the second. Every word contributes to understanding, with no redundant fluff or repetition of schema details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple, no-parameter overview tool, the description is quite complete: it lists all key figures and the intended use case. There is no output schema, so the description carries the burden of conveying return semantics, which it does adequately. A slight gap is that it does not specify output format (e.g., text vs structured object), but the enumerated metrics make it sufficient for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has no parameters (object with no properties), so there is nothing to explain. With zero parameters, the description's focus on outputs is appropriate. Schema coverage is trivially 100%, and the description confirms no input is needed, aligning with the tool's overview nature.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: it provides current key figures (open/scheduled orders, unpaid/overdue invoices, total open items). This is a specific verb+resource combination that distinguishes it from sibling tools like auftraege_suchen or rechnungen_suchen, which focus on individual records rather than an aggregate overview.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says 'Guter erster Aufruf, um zu verstehen, worum es gerade geht' (good first call to understand what's going on), which serves as a clear usage guideline for when to invoke this tool. It does not mention exclusions or alternatives, but the context of being an overview tool is sufficient for agents to choose it appropriately among siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool name clearly identifies a distinct resource (Angebot, Auftrag, Rechnung, Material, etc.) and action. Even potentially similar pairs like material_buchen and material_zuweisen are explicitly differentiated in their descriptions, so an agent can reliably select the correct tool.
All tool names follow a consistent resource_action pattern in lowercase with underscores (e.g., kunde_anlegen, material_suchen). A few status/query tools like betrieb_ueberblick and datei_stand use noun compounds, but these are consistently used for state queries and do not break the overall convention.
With 23 tools, the server falls into the 'heavy' range of 16-25. While the breadth of a handwerker management system justifies many operations, the count is high and some areas (like customer management) are underrepresented, making the set feel larger than necessary.
The core order-to-invoice workflow is well covered, but there are notable gaps: no customer search or update, no conversion from Angebot to Rechnung, and no ability to change order status. These are significant omissions that agents must work around, even though the descriptions clearly state these limitations.