Skip to main content
Glama
Sign In
immich-photo-manager

immich-photo-manager

by drolosoft
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Record action

record_action

Logs why assets were changed—album moves, date fixes, rotations—with context for audit or undo, writing only the plugin's metadata key on each asset.

Instructions

Remember something the plugin did to assets and why, for audit or undo: which album they went into and from what prompt, what date they had before a fix, why they were rotated. Side effect: writes the plugin's metadata key on each asset; other apps' keys are untouched.

Args:
    asset_ids: The assets the action touched.
    action: Short verb-like label (e.g. 'added_to_album', 'date_fixed', 'rotated').
    detail: Free text with the context worth keeping (album name, previous
        value, the user's request).

Returns: JSON with success, the number of assets recorded, the action, and a
failed array of {asset_id, error} for any asset that could not be written.
Success is true only when nothing failed.

Input Schema

NameRequiredDescriptionDefault
actionYes
detailNo
asset_idsYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.0.2

TDQS

A3.8/5.0
Behavior4/5

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

Annotations only declare a non-read-only, non-destructive operation; the description goes further by disclosing the side effect (writes the plugin's metadata key on each asset, leaving other apps' keys untouched) and the partial-failure semantics where success is true only when nothing failed. It stops short of stating permissions required or whether repeated calls append versus overwrite.

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 side effect are front-loaded, then Args and Returns are cleanly sectioned with one line each. The prose is slightly loose in the opening paragraph but no sentence is wasted.

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 annotations and an output schema, the description covers intent, side effects, and failure behavior, so an agent could call it correctly. The Returns section restates what the output schema already provides, which is redundant but harmless.

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 description coverage is 0%, so the description must carry the burden, and it does: asset_ids is framed as the assets the action touched, action is explained as a short verb-like label with concrete examples ('added_to_album', 'date_fixed', 'rotated'), and detail is scoped to context worth keeping (album name, previous value, user request). No format constraints on asset IDs are given, keeping it below 5.

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 states a specific verb-like purpose ("Remember something the plugin did to assets and why, for audit or undo") and enumerates concrete cases such as album adds, date fixes, and rotations. It is clear what the tool records, though it never contrasts itself with nearby siblings like update_asset_metadata or list_activities.

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

Usage Guidelines3/5

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

Usage is implied through examples ("which album they went into... what date they had before a fix, why they were rotated"), which conveys when an agent should log an action. There is no explicit when-not-to-use guidance and no named alternative for simpler metadata writes.

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

Deploy Server

Other Tools