Skip to main content
Glama
cfpramod

open-museum-mcp

cite

Generate citations for artworks from open-access museum collections. Choose from full (artist, title, date, museum, license, URL), caption, or short style for reuse-safe attribution.

Instructions

Render a citation for an artwork. Styles: "full" (artist, title, date, museum, license, URL), "caption" (image caption form), "short" (inline reference).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesNormalized artwork ID.
styleNofull

Implementation Reference

  • The handler function that executes the 'cite' tool logic: parses the input (id + style), fetches the artwork by id, and returns the citation string produced by the cite() utility.
    async function handleCite(args: unknown) {
      const input = CiteInput.parse(args);
      const out = await fetchAndCache(input.id);
      if (!out.ok) return errorResult(out.reason);
      return { content: [{ type: 'text' as const, text: cite(out.artwork, input.style as CiteStyle) }] };
    }
  • Zod schema for the 'cite' tool's input: object with 'id' (string matching museum ID regex) and optional 'style' enum (short/full/caption, defaulting to full).
    const CiteInput = z.object({
      id: z.string().regex(ID_REGEX),
      style: z.enum(['short', 'full', 'caption']).default('full'),
    });
  • src/server.ts:202-218 (registration)
    The tool registration in ListToolsRequestSchema: the 'cite' tool with its name, description, and input JSON schema for id and style.
    {
      name: 'cite',
      description:
        'Render a citation for an artwork. Styles: "full" (artist, title, date, museum, license, URL), "caption" (image caption form), "short" (inline reference).',
      inputSchema: {
        type: 'object',
        properties: {
          id: { type: 'string', description: 'Normalized artwork ID.' },
          style: {
            type: 'string',
            enum: ['short', 'full', 'caption'],
            default: 'full',
          },
        },
        required: ['id'],
      },
    },
  • The core cite() function that generates citation strings from an Artwork object. Dispatches to per-museum formatters (currently only 'met' overrides) for 'full' and 'caption' styles, or uses 'shortStyle' for the 'short' style.
    export function cite(artwork: Artwork, style: CiteStyle = 'full'): string {
      if (style === 'short') return shortStyle(artwork);
      if (style === 'caption') {
        const fn = PER_MUSEUM_CAPTION[artwork.museum.code] ?? metCaption;
        return fn(artwork);
      }
      const fn = PER_MUSEUM_FULL[artwork.museum.code] ?? metFull;
      return fn(artwork);
    }
  • Helper function joinNonEmpty that filters out empty/null/undefined strings and joins with a separator, used by citation formatters.
    function joinNonEmpty(parts: Array<string | undefined | null>, sep: string): string {
      return parts.filter((p): p is string => Boolean(p && p.trim())).join(sep);
    }
Behavior2/5

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

No annotations are provided, so the description must fully disclose behavioral traits. It only describes output styles but does not mention idempotency, side effects, authentication needs, or rate limits. For a read-like operation, this is a notable gap.

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 two sentences, front-loaded with the main purpose, and every word adds value. No redundancy or unnecessary detail.

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?

For a simple tool with two parameters and no output schema, the description covers the essential purpose and parameter variations. It omits details about the return format (e.g., plain text vs. JSON) but is otherwise complete for typical use.

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?

While schema coverage is 50%, the description adds meaning to the 'style' parameter by explaining what each enum value produces ('full' includes artist, title, etc.; 'caption' for image captions; 'short' for inline references). The 'id' parameter is adequately described in the schema.

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 clearly states 'Render a citation for an artwork' and lists three distinct styles ('full', 'caption', 'short'), making the tool's purpose specific and differentiating it from sibling tools like 'discover_random' or 'search_artworks'.

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 explains each style's purpose ('full' includes all fields, 'caption' for image captions, 'short' for inline references), providing clear context for when to use each variant. However, it does not explicitly state when not to use this tool or alternative tools, though sibling tools are sufficiently different.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/cfpramod/open-museum-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server