Update a memory

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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false and openWorldHint=true, so the write/idempotency/safety profile is covered. The description adds the deprecation warning and the raw HTTP method, which is genuinely useful context, but it discloses nothing about update semantics (partial vs full replacement) or what happens to unspecified fields.

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?

Very short: one sentence of substance plus an operation/tag line and a deprecation line. The opening 'Update a memory' merely repeats the title and could be dropped, but otherwise there is no wasted prose and the key facts are front-loaded.

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 with no output schema, the description should explain enough to call it safely. It leaves the most important agent question unanswered — if this is deprecated, what replaces it? — and gives no update semantics (partial vs full, effects on unspecified fields).

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 nominally documents all four parameters, though the field descriptions are bare restatements like 'isSaved (request body)'. The description adds no parameter meaning at all — no format hints for memoryAt/seenAt, no note that id must be a valid memory UUID. Baseline 3 per the high-coverage rule.

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 (update) plus resource (memory) and scopes it to a single record by ID, and it names the underlying PUT /memories/{id} operation. It is distinguishable from immich_get_memory/immich_delete_memory by the verb, but it does nothing to differentiate itself from other update_* siblings or explain what this tool does that they don't.

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 indication of which fields can be changed, whether the update is partial or full, or permissions required. The only directive is a vague 'DEPRECATED — prefer the replacement operation if one exists,' which names no replacement, so an agent is told to avoid the tool without being told what to use instead.

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