immich_search_smart

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

No annotations are provided, so the description carries the full burden. It does disclose the return content ('matching photos with metadata') and the effect of withImages, which is useful. It says nothing about result limits, ordering, permissions, or whether the CLIP index must be built, leaving meaningful behavioral gaps for an unannotated tool.

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?

Two compact sentences with the core purpose front-loaded, and the examples are short enough to aid rather than bloat. Every element is functional, though the example list is slightly padded.

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?

With no output schema, the description appropriately states that results come back as photos with metadata, and all four parameters are documented in the schema. It is nearly complete, missing only ranking/pagination context that an agent might want for a search tool.

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 baseline is 3. The description adds query examples and clarifies what withImages does, but contributes no extra meaning for size or personIds beyond what the schema already documents.

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 and resource ('Search photos') plus the mechanism ('natural language (CLIP)'), which cleanly separates it from keyword/metadata search. It does not explicitly name sibling search tools (immich_search_metadata, immich_search_people), so the differentiation is implied rather than stated.

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?

The examples ('sunset at beach', 'birthday cake') imply the kind of query to use and 'Use withImages=true to see thumbnails' is an actionable hint, but there is no guidance on when to choose this over the other search tools or what the default response omits. Usage is implied, not specified.

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