Skip to main content
Glama

Mandanten suchen

mandant_search
Read-only

Sucht Mandanten über Mandantennummer, Name, Tags oder Sachbearbeiter und nennt für jeden Treffer die passende Spalte. Nächster Schritt mit der gefundenen mandantennummer: document_create erzeugt daraus eine Rechnung, Mahnung, Zahlungserinnerung oder Gutschrift, mandant_get liefert die vollständigen Stammdaten, letter_create_draft schreibt einen normalen Brief. EN: Searches clients (Mandanten) by client number, name, tags or case handler and names the matching column for each hit. Next step with the matched mandantennummer: document_create turns it into an invoice, dunning letter, payment reminder or credit note, mandant_get returns the full record, letter_create_draft writes a normal letter.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "mandant_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoStandard 20, maximal 100. EN: Default 20, maximum 100.
queryYes
sinceNoNur Mandanten, die seit diesem Zeitpunkt angelegt wurden (ISO 8601). EN: Only clients created since this time (ISO 8601).
offsetNoVersatz für die Seitennavigation. Standard 0. EN: Offset for pagination. Default 0.
reasoningNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile needs no restating. The description adds that each hit names the matching column and that pagination exists implicitly, but says nothing about match mode (exact vs. fuzzy), result ordering, or what happens when the query is ambiguous.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is correctly front-loaded, but the entire text is duplicated verbatim in German and English, roughly doubling token cost with zero added information. Each language block is tight; the duplication is the waste.

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?

With five parameters and no output schema, the description should explain what a hit looks like, but 'nennt für jeden Treffer die passende Spalte' (names the matching column) is cryptic and doesn't tell the agent the result shape or whether to page via offset/limit. The remaining gaps are moderate rather than blocking.

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 coverage is 60%: limit, since and offset are documented in-schema, but the required 'query' and 'reasoning' have no descriptions. The description compensates for the opaque query parameter by naming the fields it can match against (number, name, tags, case handler), which is genuine meaning beyond the schema.

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?

States a specific verb and resource and enumerates the searchable attributes (client number, name, tags, case handler), which an agent can act on immediately. It differentiates itself from mandant_get by contrasting lookup vs. full record, but never mentions mandant_list, the closest competing sibling for retrieving clients.

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 describes the follow-up path: once a mandantennummer is found, it names document_create, mandant_get and letter_create_draft and what each is for. That is real routing guidance, but it only covers what to do after this tool, not when to choose it over mandant_list or how to handle zero/ambiguous results.

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.