Skip to main content
Glama
Foto MCP Server
by thesven

foto_watch_directory

Scan a local photo export folder to inspect new images, merge XMP ratings and color labels, extract EXIF metadata, suggest tags, and generate preview thumbnails for publication drafts.

Instructions

Scan a local studio watch directory (e.g. Lightroom or Capture One export folder), auto-inspect new photo exports, merge .xmp sidecar ratings/color labels, extract camera EXIF, suggest curated tags, generate color-corrected preview thumbnails, and format publication drafts.

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": {
      "directoryPath": "<directoryPath>"
    },
    "name": "foto_watch_directory"
  }
}

Input Schema

NameRequiredDescriptionDefault
maxPhotosNoMaximum number of photos to scan (default: 50)
minRatingNoOptional minimum XMP star rating filter (1 to 5)
colorLabelNoOptional XMP color label filter (e.g. 'Select', 'Red', 'Green')
directoryPathYesPath to local directory to scan for photography exports
includePreviewNoWhether to generate base64 multimodal preview thumbnails (default: true)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv3.0.1

TDQS

C2.8/5.0
Behavior2/5

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

With no annotations at all, the description carries the full burden and leaves key behavior undisclosed: it does not say whether merging XMP or generating thumbnails writes files to disk, whether the "watch" is a one-shot scan or a persistent watcher, or what happens when maxPhotos truncates a large folder. The most consequential facts for a filesystem-touching tool are absent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The action is front-loaded with the verb "Scan," which is good, but the remainder is a single run-on list of seven comma-linked capabilities with no grouping. Every item is plausibly relevant, yet the wall of clauses makes it harder to extract the primary purpose and the optional extras.

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

Completeness2/5

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

For a five-parameter, no-output-schema, no-annotation tool that touches the local filesystem, the definition omits the return shape (a scan report? merged metadata? draft text?) and the side effects. An agent cannot predict what it will get back, which is a material gap when nothing else describes the output.

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?

All five parameters are already documented at 100% schema coverage, so the schema does the heavy lifting. The description only loosely maps to them (ratings/color labels, preview thumbnails) and adds no format, path-syntax, or interaction detail such as whether minRating also filters photos lacking XMP.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource ("Scan a local studio watch directory") and enumerates the sub-operations it performs (XMP merge, EXIF extraction, tag suggestion, thumbnail generation, draft formatting). No sibling operates on a local directory, so the scope is distinguishable, though the catalog of seven operations makes it read more like a pipeline than a single tool.

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

Usage Guidelines2/5

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

There is no statement of when to prefer this over a narrower sibling such as foto_parse_xmp or foto_inspect_image, and no mention of prerequisites like authentication, studio context, or a prior login. The agent must infer that this is the bulk/offline-export entry point rather than an on-demand single-image tool.

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