Skip to main content
Glama
malkreide

swiss-cultural-heritage-mcp

by malkreide
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

heritage_get_publication

Read-onlyIdempotent

Retrieves selected publication metadata from the Swiss National Library by OAI identifier, returning normalized Dublin Core fields for title, creators, publisher, year, and subjects.

Instructions

Ruft die Metadaten einer Publikation der NB ab — ausgewählte MARC21-Felder.

Die Quelle liefert MARCXML. Dieses Werkzeug bildet daraus eine Auswahl von Feldern auf Dublin-Core-ähnliche Schlüssel ab: Titel, Urheber·innen, Mitwirkende, Verlag, Erscheinungsjahr, Typ, Umfang, Sprache, Schlagwörter, Beschreibung, Rechte, Reihe und Identifier.

Was NICHT enthalten ist: alles ausserhalb dieser Auswahl — Kontrollfelder, die Ausgabebezeichnung (MARC 250), Erscheinungsverlauf, lokale Felder. «Vollständige Metadaten» wäre also falsch, und die Antwort darf nicht als der ganze Katalogsatz gelesen werden. Wer den braucht, nimmt den Permalink aus identifier und geht an die Quelle.

Args: params (PublicationDetailInput): - identifier (str): OAI-ID aus heritage_search_helveticat - response_format: 'markdown' oder 'json'

Returns: str: Ausgewählte, auf DC-Schlüssel normalisierte Felder — nicht der vollständige Katalogsatz.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
paramsYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.3.0
    • addedOutput schema / $defs
      Added value: +{
+  "ResultEnvelope": {
+    "description": "Einheitlicher Response-Envelope für Such-/Listen-Tools.",
+    "properties": {
+      "count": {
+        "description": "Anzahl zurückgegebener Einträge",
+        "title": "Count",
+        "type": "integer"
+      },
+      "has_more": {
+        "default": false,
+        "description": "Weitere Ergebnisse verfügbar",
+        "title": "Has More",
+        "type": "boolean"
+      },
+      "match_type": {
+        "default": "exact",
+        "description": "Trefferart (ARCH-003): 'exact' = direkte Suche, 'fuzzy' = gelockerte/erweiterte Suche nach 0 exakten Treffern, 'none' = keine Treffer",
+        "enum": [
+          "exact",
+          "fuzzy",
+          "none"
+        ],
+        "title": "Match Type",
+        "type": "string"
+      },
+      "meta": {
+        "anyOf": [
+          {
+            "additionalProperties": true,
+            "type": "object"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "description": "Tool-spezifische Zusatzfelder",
+        "title": "Meta"
+      },
+      "offset": {
+        "anyOf": [
+          {
+            "type": "integer"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "description": "Paginierungs-Offset",
+        "title": "Offset"
+      },
+      "results": {
+        "description": "Datensätze (quellnah)",
+        "items": {
+          "additionalProperties": true,
+          "type": "object"
+        },
+        "title": "Results",
+        "type": "array"
+      },
+      "source": {
+        "anyOf": [
+          {
+            "$ref": "#/$defs/SourceInfo"
+          },
+          {
+            "items": {
+              "$ref": "#/$defs/SourceInfo"
+            },
+            "type": "array"
+          }
+        ],
+        "description": "Quelle(n) inkl. Lizenz",
+        "title": "Source"
+      },
+      "total": {
+        "anyOf": [
+          {
+            "type": "integer"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "description": "Gesamtzahl upstream verfügbar",
+        "title": "Total"
+      }
+    },
+    "required": [
+      "source",
+      "count"
+    ],
+    "title": "ResultEnvelope",
+    "type": "object"
+  },
+  "SourceInfo": {
+    "description": "Provenienz und Lizenz einer Datenquelle.",
+    "properties": {
+      "license": {
+        "title": "License",
+        "type": "string"
+      },
+      "name": {
+        "title": "Name",
+        "type": "string"
+      },
+      "url": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Url"
+      }
+    },
+    "required": [
+      "name",
+      "license"
+    ],
+    "title": "SourceInfo",
+    "type": "object"
+  }
+}
    • addedOutput schema / properties / result / anyOf
      Added value: +[
+  {
+    "$ref": "#/$defs/ResultEnvelope"
+  },
+  {
+    "type": "string"
+  }
+]
    • removedOutput schema / properties / result / type
      Removed value: -"string"
  2. First observedv0.2.0

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already mark the tool as read-only and idempotent, but the description adds substantial behavioral context: the source is MARCXML, the output is a selective Dublin-Core-like mapping, and it explicitly lists excluded fields such as MARC 250, control fields, and local fields. The warning not to interpret the response as the complete catalog record is particularly valuable.

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?

The description is compact relative to the ground it covers: purpose, field selection, exclusion list, and docstring-style Args/Returns sections. Every sentence earns its place, and the most important misuse risk—treating the result as the full catalog record—is clearly emphasized.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only retrieval tool with one required identifier plus an optional format, the description is complete: it states the input provenance, the output mapping, the excluded fields, and the fallback for full metadata. Since an output schema exists, the absence of a detailed return schema is not a gap.

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?

The Args block names both parameters and restates what the embedded schema already provides: identifier is the OAI-ID from heritage_search_helveticat and response_format is 'markdown' or 'json'. It adds no new parameter-level semantics, such as how the markdown and json outputs differ, so it meets the baseline but does not exceed it.

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?

The description names a concrete operation: 'Ruft die Metadaten einer Publikation der NB ab' and immediately scopes it to 'ausgewählte MARC21-Felder'. It also explicitly distinguishes the result from a full catalog record, making it easy to separate from sibling search tools.

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?

The description implies the right entry point by saying the identifier comes from heritage_search_helveticat, and it gives a clear alternative for full metadata: 'Wer den braucht, nimmt den Permalink aus identifier und geht an die Quelle.' It does not enumerate all sibling tools, but for its scope the guidance is clear.

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