Skip to main content
Glama
rt-imaging-mcp

rt-imaging-mcp

by MLwithDyy

Read allowlisted DICOM metadata

dicom_get_metadata
Read-onlyIdempotent

Reads allowlisted technical attributes from one DICOM file using a root-relative path and requested keywords, returning PHI-safe metadata without patient identifiers or pixel data.

Instructions

Read allowlisted technical attributes of one DICOM file (path relative to the root).

Use dicom_list_allowed_tags to see which keywords are allowed. Requesting any other keyword fails. Patient identifiers and pixel data are never 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": {
      "path": "<path>"
    },
    "name": "dicom_get_metadata"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYes
keywordsNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.0.1

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the description's value is in the added behavior: an allowlist gate that makes out-of-list keywords fail, and the privacy guarantee that patient identifiers and pixel data are never returned. That is meaningful disclosure beyond the annotations, though failure modes such as a missing path are left implicit.

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?

Two short sentences, zero filler, and the core action plus its precondition are front-loaded. The allowlist caveat is placed exactly where it is needed before the agent picks keywords.

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?

With an output schema present, return-value detail is unnecessary, and the description covers path resolution, the allowlist constraint and privacy exclusions. The one real gap is the semantics of the optional keywords parameter when omitted, which an agent would need before calling.

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?

Schema description coverage is 0%, so the description carries the burden. It clarifies 'path' as root-relative and constrains 'keywords' to the allowlisted set with failure otherwise, which is genuinely useful. However, it never explains the default null value (whether omitting keywords returns all allowed tags), leaving the second parameter's primary behavior ambiguous.

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 ('Read allowlisted technical attributes of one DICOM file') plus scope ('one file', 'path relative to the root'). It also explicitly routes the reader to the sibling dicom_list_allowed_tags for the allowlist, so an agent can separate this from the listing tool 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?

Gives clear context for use: read metadata of a single DICOM file, and consult dicom_list_allowed_tags first to learn valid keywords. It also states the negative condition that requesting any other keyword fails. It stops short of stating when-not-to-use (e.g. for whole-directory inspection, where dicom_scan_directory would be the choice), so not a 5.

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