immich-photo-manager

Overview Schema Source Related Servers Discussions Admin

Get duplicates

get_duplicates

Read-only

Retrieves ML-detected duplicate photo groups so you can review repeated images before resolving them; optionally restrict results to a specific album. Read-only.

Instructions

Get ML-detected duplicate asset groups (same image stored more than once). Use this to review potential duplicates before resolving them with resolve_duplicates. Requires Immich ML service. Note: "duplicates" means the same picture, not the same person — for people use get_album (assets[].people) or get_asset_faces. Read-only.

Args:
    album_id: Optional. Restrict to groups that touch this album; each group then also
        reports which of its assets are inside/outside the album.

Returns: JSON array of duplicate groups (each with duplicateId, assets array, and similarity scores).

Input Schema

Name	Required	Description	Default
`album_id`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv2.0.1Sep 1, 2026
- addedInput schema / properties / album_id
```
Added value: +{
+  "default": "",
+  "title": "Album Id",
+  "type": "string"
+}
```
Addedv1.2.1May 17, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the 'Read-only' sentence is redundant. What the description adds beyond that is genuinely useful: results depend on the ML service being available, and detection is ML-based rather than exact-hash, which affects how much an agent should trust group membership. It stops short of saying whether groups can be stale or how similarity is thresholded.

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, then usage, then the disambiguation note, then args and return value — a sensible order. A few sentences do not earn their place: 'Read-only' duplicates the annotations and the closing Returns sentence restates an available output schema.

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 single optional-parameter read tool, the description covers purpose, prerequisite, alternative tools, parameter effect, and return shape. An agent can decide whether to call it and interpret the response without opening anything else.

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% — the schema only carries 'Album Id' with a default of empty string — so the description must compensate. It does explain the filtering behavior and the extra per-group inside/outside reporting, which is real meaning the schema lacks. However, it never says what the empty-string default means (presumably 'all groups'), which is the one thing an agent must infer.

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 ('Get ML-detected duplicate asset groups (same image stored more than once)') and immediately disambiguates the term 'duplicates' from people duplicates, which is the exact ambiguity an agent would hit with this name. It also names the paired sibling resolve_duplicates, so the tool is identifiable without opening the schema.

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?

Explicitly says when to use it ('review potential duplicates before resolving them with resolve_duplicates') and when not to ('for people use get_album (assets[].people) or get_asset_faces'), naming the actual alternatives. It adds a prerequisite too ('Requires Immich ML service'), which is real routing information.

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

Deploy Server