search_explore

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 explicitly declares 'Read-only,' so the agent knows this is a safe read. It also discloses a non-obvious edge case — cities only appear once they hold at least 5 assets, so small libraries can come back empty — and explains the 'one representative asset per city/concept' selection behavior. This goes well beyond what structured fields could have conveyed.

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 description is front-loaded with the core purpose, followed by usage guidance, then edge-case and safety notes, each earning its place. The only redundancy is the 'Returns:' section, which partially overlaps with the existing output schema — though it does add a concrete example field name ('exifInfo.city') and the asset_id pairing.

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 zero-parameter, read-only tool with an output schema, nothing an agent needs to invoke it correctly is missing: semantics, usage timing, edge-case empty returns, and safety are all covered. The missing annotations are fully compensated by the explicit 'Read-only' statement and the small-library warning. The output schema handles the detailed return structure.

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?

The tool takes zero parameters and the schema's properties object is empty, so the 0-param baseline of 4 applies and there is no parameter gap to compensate for. The description instead uses the space to clarify what the response represents, which is appropriate. No parameter-level meaning is missing.

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 and resource — 'Overview of what the library contains, grouped by explore field' — and grounds it in Immich's Explore page. It answers 'what is in here?' in one call, clearly distinguishing this library-wide overview from the targeted search_* siblings such as search_metadata and search_cities.

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?

'Use this to get oriented in an unknown library before searching for anything specific' is an explicit, actionable when-to-use instruction. It implies a temporal when-not — once you want something specific, move on to targeted search tools — but it never names an alternative sibling, leaving the agent to infer which search_* tool to use next. Clear context with an implied exclusion, but no explicit alternatives.

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