get_duplicates

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

With no annotations provided, the description carries the full burden and does well: it discloses that the operation is read-only, that it depends on the ML service, and that results are duplicate groups with similarity scores. It does not mention failure modes or authorization, but the key behavioral traits are covered.

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?

The description is well-organized with a front-loaded purpose, an explicit note, an Args section, and a Returns section. Every sentence contributes meaningful information, and the format makes it easy for an agent to scan.

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?

Given only one optional parameter and an output schema, the description fully covers the tool's behavior, input semantics, return shape, and dependency. An agent has enough context to decide whether and how to invoke this tool correctly.

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 0%, so the description must compensate, and it does for the only parameter. It explains album_id is optional, restricts to groups touching the album, and changes the returned group metadata to include inside/outside asset status.

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?

The description uses a specific verb and resource ('Get ML-detected duplicate asset groups') and clarifies the meaning as 'same image stored more than once.' It also explicitly distinguishes itself from related tools like get_album and get_asset_faces, so an agent can immediately tell what this tool is for.

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?

It clearly states when to use the tool ('review potential duplicates before resolving them with resolve_duplicates'), when not to use it ('not the same person'), and names alternative tools for the other case. It also flags the dependency on the Immich ML service.

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