ReftrixMCP

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

While annotations indicate read-only/idempotent status, the description adds valuable algorithmic transparency: DINOv2 visual embeddings, HNSW search methodology, and specific RRF fusion weights (text 40% + vision 30% + fulltext 30%). This discloses how results are ranked and combined, though it omits rate limits or result format details.

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?

Four sentences with zero waste: purpose declaration, input specification, pure visual search mechanics, and hybrid search behavior. Technical details (DINOv2, RRF weights) are densely packed but clearly presented. Front-loaded with the core function.

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?

Given the rich schema (5 parameters, 100% coverage) and complex hybrid search behavior, the description adequately covers input requirements and search logic. However, without an output schema, it could benefit from describing what constitutes a 'design section' result or 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?

With 100% schema coverage, the baseline is 3. The description adds semantic value by explaining that the image parameter drives DINOv2 visual embedding generation and that the query parameter triggers multi-source RRF fusion, providing behavioral context beyond the schema's format specifications.

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 searches for visually similar design sections from images, using specific technical mechanisms (DINOv2, HNSW) that distinguish it from text-based siblings like search.unified or layout.search. It precisely identifies the resource (design sections) and operation (visual similarity search).

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 effectively explains when to use the optional text query parameter (triggering hybrid RRF fusion) versus image-only search. However, it lacks explicit comparison to sibling alternatives like design.compare or design.similar_site for determining when this specific tool is preferred.

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