Apply edits to an existing asset

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

Annotations already cover the safety profile (mutation, idempotent, non-destructive), so the bar is lower. The description adds the HTTP semantics (PUT /assets/{id}/edits) and that edits are applied as a series, which hints at replace semantics, but it does not state whether existing edits are overwritten or appended, nor whether the original file is modified.

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

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

Compact and front-loaded, but the opening line duplicates the title verbatim before the more useful sentence, which is a redundant sentence fragment. The remaining content (action list, endpoint metadata) is tight and earns its place.

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

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

For a mutation tool, the annotations plus full schema coverage cover most needs, and there is no output schema to explain. However, key behavioral questions an agent would care about — whether these edits replace prior edits, persist non-destructively, or require ownership/permission — are left unaddressed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents id, edits, and the nested action/parameter shapes including the crop/rotate/mirror enum. The description merely restates the action types the schema already enumerates, adding no syntax or constraint detail. Baseline 3 applies when the schema does the heavy lifting.

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

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

States a specific verb and resource ('Apply edits to an existing asset') and enumerates the action types (crop, rotate, mirror), so the agent understands this mutates an asset's edits. It stops short of naming or distinguishing the close siblings immich_get_asset_edits and immich_remove_asset_edits, so it is clear but not fully differentiated.

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

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

The description says what the tool does but never states when to reach for it versus alternatives like immich_get_asset_edits (read current edits), immich_remove_asset_edits (clear them), or immich_update_asset (other metadata). No prerequisite or exclusion is given, leaving selecting between these siblings to inference.

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