Skip to main content
Glama

skkg_find_terms

skkg_find_terms
Read-onlyIdempotent

Find SKKG vocabulary terms by label prefix to retrieve filter values, IDs, hierarchy paths, usage counts, and applicable search filters.

Instructions

Find terms of SKKG's vocabularies by label, to use as filter values. Labels are German; English and French labels match where SKKG has them. Each word matches the start of a word in a label ("Radier" finds "Radierung"). Terms in use come first; among them, exact label matches, then the terms used most. Each term carries its id, its path in the hierarchy, its year range (epochs), its matches in GND, AAT, or Wikidata, how many objects use it (an image licence: objects whose primary image has it), and filters: every search parameter that takes it, each with its tool and the total that filter reports for the term (skkg_search_objects; skkg_search_provenance for the vocabularies of provenance periods; skkg_search_actors for gender, and for a country code both nationality and place_country; skkg_search_literature for literature types; skkg_search_exhibitions for the types, status, and "intern" or "extern" of exhibitions). Many vocabularies have no filter. Currency terms have none either: currency of skkg_search_provenance takes the codes of the prices ("CHF", "DEM") and SKKG's labels of them. With id, returns one term with its broader and narrower terms. With only vocabulary, lists that vocabulary. To search objects, use skkg_search_objects; its term filters take these labels or ids directly.

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": "skkg_find_terms"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoA term id ("type/21087/140347") or its data.skkg.ch IRI: returns that term with its broader and narrower terms
langNoLanguage of vocabulary labels. Most vocabularies, materials and object types among them, have German labels only, which are returned whatever the language; titles and texts stay as recordedde
limitNoTerms per page; with `id`, narrower terms per page
queryNoLabel words, e.g. "Radierung" or "Silber"; each matches as a prefix. Every word must occur; "a phrase" matches in order; a trailing * matches a prefix; OR between two words matches either; NOT before a word excludes it
offsetNo
vocabularyNoRestrict to one vocabulary: object_type (object types, hierarchical ("Malerei" > "Ölmalerei")); material (materials, hierarchical); technique (techniques); epoch (epochs, with a year range); production_role (roles of creators ("Künstler:in", "Verlag")); attribution (attribution qualifiers ("zugeschrieben", "nach")); acquisition_type (how SKKG acquired an object); object_copyright (copyright status of objects); image_license (image licences); provenance_status (provenance research status); redaction_status (documentation status of records); date_basis (what a dating rests on ("datiert", "Expertise Fachperson")); condition (condition of objects ("Stabil", "Gut")); object_reference_type (kinds of links between objects); owner_type (kinds of owner in provenance periods); certainty (certainty of provenance periods); holding_kind (kinds of holding (ownership, custody)); transaction_type (how an owner acquired an object); source_type (sources of provenance periods); date_qualifier (qualifiers of provenance dates ("vor", "nach")); currency (currencies of prices); literature_type (kinds of publication); literature_place (places of publication, hierarchical); author_role (roles of authors of publications); exhibition_type (kinds of exhibition); exhibition_status (status of exhibitions); internal_external (SKKG's "intern" or "extern" for exhibitions); gender (gender of persons); country (countries, e.g. nationalities of persons). Default all, which includes SKKG's unnamed schemesall

Output Schema

NameRequiredDescriptionDefault
termNoThe term asked for with `id`
totalYes
offsetYes
appliedYes
broaderNoWith `id`: the broader terms, top-level first
resultsNoThe terms found; absent with `id`
has_moreYes
narrowerNoWith `id`: the narrower terms, most used first; `total` counts them
returnedYes
warningsNo
data_as_ofNo
next_offsetNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.0

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive), yet the description adds substantial behavior of its own: per-word prefix matching, exact-phrase, trailing `*`, OR, and NOT semantics, plus result ordering (terms in use first, then exact label matches, then most-used). It also enumerates the returned fields (id, hierarchy path, year range, GND/AAT/Wikidata links, usage counts, `filters`). The only missing piece is pagination behavior for the non-`id` modes.

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?

Front-loaded with purpose and matching rules, and nearly every clause carries operational information (ordering, filters, sibling handoff). It is dense and long, with the long parenthetical enumerating which filter lives in which sibling tool being the one stretch that reading flow suffers on, but little is genuinely dispensable.

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 six-parameter, mode-switching lookup tool with an output schema and annotations already supplied, the description covers what the agent still needs: matching syntax, ordering, what each term carries, and how results map onto other tools' filters. Nothing required to call it correctly is missing.

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 already high at 83%, so the schema carries most parameter detail. The description still adds cross-parameter behavior the schema cannot express: the id-mode returns broader and narrower terms, and the vocabulary-only mode lists a vocabulary, and currency terms are noted as having no filter because that filter takes price codes instead.

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 ("Find terms of SKKG's vocabularies by label") plus the downstream purpose ("to use as filter values"), and explicitly distinguishes itself from skkg_search_objects as the place to actually search. An agent can route between lookup and search without ambiguity.

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

Usage Guidelines5/5

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

Gives explicit mode selection: with `id` returns one term plus broader/narrower, with only `vocabulary` lists that vocabulary, and otherwise it is a label lookup. It also names the alternative ("To search objects, use skkg_search_objects; its term filters take these labels or ids directly"), which tells the agent both when to use this tool and how its output feeds the sibling.

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