Skip to main content
Glama
german-archives-mcp
by ianderso

nrw_image

Idempotent

Download a Landesarchiv NRW register page image to a specified JPEG file so the page can be read and cited.

Instructions

Download one page image of a Landesarchiv NRW register, so it can be read.

This is the step that makes a register evidence: read the page before citing it. page is the image's place in the viewer, not the number written on the page. Saves a new .jpg or .jpeg file, never returned inline: not hidden, not under ~/Library, and inside the operator's download folder when one is set. Cite by the citation returned.

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": {
      "item": "<item>",
      "destination": "<destination>"
    },
    "name": "nrw_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
itemYesThe `mets` address from nrw_search, e.g. 'https://www.landesarchiv-nrw.de/digitalisate/Abt_Rheinland/PA_2104/~002/00267/mets.xml', or its DFG-Viewer link.
pageNoWhich image, 1-based, in the order of the archive's viewer.
destinationYesAbsolute path of a new .jpg file, e.g. '/path/to/images/PA2104-267-bild-12.jpg'. The directory must exist and the file must not: nothing is overwritten.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

Beyond the annotations, the description discloses the concrete write behavior: a new .jpg/.jpeg is saved to disk, the image is never returned inline, the file is not hidden or placed under ~/Library, and it lands in the operator's download folder when one is set. It also notes a `citation` is returned for reuse. It does not mention auth, rate limits, or failure modes for out-of-range pages, keeping this below a 5.

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?

The purpose and the workflow placement are front-loaded, and no sentence is filler. The 'not hidden, not under ~/Library' clause is slightly cryptic and platform-specific, which costs a point on tightness but still conveys real file-placement constraints.

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 three-parameter write tool with a fully documented schema and no output schema, the description covers what is produced (a file on disk plus a returned `citation`) and where it goes, which is what an agent needs to call it correctly. Nothing critical is missing, though error behavior for invalid pages or existing files is left unstated.

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 100%, so the baseline is 3, but the description earns above baseline by clarifying that `page` is the image's position in the viewer rather than the number printed on the page — a distinction the schema text does not make. It does not elaborate on `item` or `destination` beyond what the schema already states.

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 first sentence names a specific verb ('Download') and resource ('one page image of a Landesarchiv NRW register') with an explicit scope limit of one page, and it links to the sibling workflow by naming the `mets` address from nrw_search. An agent can distinguish this from nrw_search without opening either schema.

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?

"This is the step that makes a register evidence: read the page before citing it" tells the agent where this fits in the workflow — after finding an item, before citing. It gives clear positive guidance but states no exclusion or failure case (e.g., what to do if the page does not exist).

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