search_smart

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

With no annotations provided, the description carries the full burden and meets it: it declares 'Read-only,' discloses the server-side dependency, and flags that the ocr parameter requires OCR enabled, pointing to get_capabilities as a check. It also reveals non-obvious behavior — results are 'ranked by visual similarity to the query.'

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?

Every sentence earns its place: purpose, usage condition, alternative, prerequisite, and safety are front-loaded before the structured Args block. The per-line parameter format is compact and consistent, with examples and constraints inline, and the Returns line closes with the essential output shape.

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 12-parameter tool with no annotations and zero schema descriptions, the description covers what the tool does, when to use it, the alternative, prerequisites, every parameter's semantics, and the return shape. Since an output schema exists for detailed return structure, the brief Returns line is sufficient; nothing needed to select or invoke the tool correctly is missing.

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 Args block must compensate — and it fully does. Every one of the 12 parameters gains meaning beyond the schema titles: the ALL constraint on person_ids, ISO date semantics for taken_after/taken_before, source hints like 'ids from list_people' and 'ids from list_tags,' and the 1-200 range for size.

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?

Opens with a specific verb and resource — 'AI-powered visual search using CLIP embeddings' — and clarifies the input modality with concrete natural-language examples. It explicitly differentiates itself from sibling search_metadata ('For structured criteria (city, camera, date), use search_metadata instead'), so an agent can select it without ambiguity.

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?

Gives an explicit when-to-use rule ('Use this when describing what a photo looks like in natural language') and names the exact alternative for structured criteria. It also states the prerequisite ('Requires Immich ML service with Smart Search enabled'), which tells the agent when the tool is available.

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