Create a memory

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, and openWorldHint=true, so the safety/behavioral profile is covered by structured data. The description adds nothing beyond the endpoint line: no auth requirements, no side effects, no note on what the memory becomes visible as or whether it can be undone.

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?

Short and front-loaded, with the create verb leading and the endpoint/tag line trailing. The opening sentence merely restates the title, a small redundancy, but there is no padding beyond that.

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 an 8-parameter mutation with a nested object (data.year), a const enum-ish type, and several optional timestamps, plus no output schema, the description is far too thin. It never explains the on_this_day memory concept, the meaning of memoryAt/showAt/hideAt/seenAt, or defaults, leaving the agent guessing on the core semantics.

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 nominally 100%, but the schema descriptions are boilerplate ('(request body)'), so the schema carries little real meaning. Worse, the description names 'name' and 'description' fields that do not exist in the schema and omits the actual required fields (data.year, memoryAt, type const 'on_this_day'), which is actively misleading rather than merely unhelpful.

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 opens with a specific verb+resource ('Create a new memory') and the POST /memories operation line anchors it precisely, so the agent knows this is the creation counterpart to update/delete/get memory. However, it does not distinguish itself from siblings like immich_add_memory_assets or immich_update_memory, and the fields it names (name, description) do not match the actual schema, muddying the picture.

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?

There is no when-to-use guidance, no prerequisites, and no routing to alternatives. The agent must infer on its own that adding assets to an existing memory belongs to immich_add_memory_assets rather than this tool.

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