immich-mcp

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

Annotations provide readOnlyHint=true, indicating this is a safe read operation. The description adds useful context about the search methodology (CLIP/ML) and the natural language query format, which goes beyond the annotations. However, it doesn't disclose behavioral details like rate limits, authentication needs, or what happens with empty results. No contradiction with annotations exists.

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 perfectly concise: one sentence stating the tool's purpose and methodology, followed by a practical example in parentheses. Every word earns its place, and the information is front-loaded with no wasted text. The structure guides the user immediately to the core functionality.

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 search tool with good annotations (readOnlyHint) and high schema coverage, the description adequately covers the main use case. However, with no output schema, it doesn't explain what results look like (e.g., format, fields returned). The description could benefit from mentioning result limitations or ordering, but it's minimally complete for basic usage.

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 80%, so the schema already documents most parameters well. The description emphasizes the 'query' parameter's natural language nature with examples, adding value beyond the schema's 'Natural language description' text. It doesn't explain other parameters like 'type', 'is_favorite', or pagination, but with high schema coverage, baseline 3 is appropriate.

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 clearly states the tool's purpose: 'Semantic search using CLIP/ML' with the specific action 'Describe what you're looking for in natural language.' It distinguishes from sibling tools like 'immich.search.metadata' (likely metadata-based search) and 'immich.search.explore' (unclear but different). The examples ('sunset at the beach', 'birthday party') reinforce the natural language query approach.

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 description provides clear context for when to use this tool: for semantic search with natural language queries. It doesn't explicitly mention when NOT to use it or name specific alternatives (like 'immich.search.metadata'), but the natural language focus strongly implies this is for content-based rather than metadata-based searches. No prerequisites or exclusions are stated.

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