Create a stack

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

Beyond the annotations (destructiveHint=false, openWorldHint=true, idempotentHint=false), the description discloses a non-obvious side effect: if an asset is a primary asset of an existing stack, that existing stack is absorbed into the new one. This is valuable behavioral context an agent could not infer from the schema. There is a mild tension with destructiveHint=false, since an existing stack effectively disappears, but the description does surface the effect rather than hide it.

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 merge caveat is front-loaded in the second sentence and the text is short. However the leading "Create a stack" line merely repeats the title, and the trailing "Immich operation: POST /stacks · tag: Stacks" duplicates routing metadata that already lives in structured fields.

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 single-parameter mutation with annotations present and no output schema, the merge semantics are the most important thing to document and they are covered. The completeness is undercut by the fabricated "name" field and by no mention of permission/auth requirements or what the created stack response looks like.

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?

With 100% schema coverage the baseline is 3, but the description actively introduces a mismatch: it says to provide "a name and a list of asset IDs," while the schema accepts only assetIds and sets additionalProperties=false. An agent following the prose would attempt an invalid parameter, so this is worse than schema-only documentation.

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 states a specific verb+resource ("Create a new stack") plus the inputs that define it, so an agent understands this groups asset IDs into a stack. It does not differentiate from nearby siblings such as immich_create_album or immich_create_tag, which also create containers from assets.

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?

Usage is implied by "Create a new stack by providing a name and a list of asset IDs" and the merge note hints at overlap handling, but there is no explicit when-to-use vs. when-not, and no pointer to alternatives like immich_update_stack or immich_remove_asset_from_stack.

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