ReftrixMCP

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

Description excellently discloses the similarity algorithm (section embeddings, mean pooling, pgvector HNSW, RRF 3-source fusion with specific weights) beyond the readOnly/idempotent annotations. However, it doesn't explicitly mention the 404 error case for unanalyzed URLs or describe the return format, which would be helpful given no output schema 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 bilingual format efficiently packs technical implementation details (embedding models, fusion weights) into two sentences per language. While dense with implementation specifics (DINOv2, pgvector, RRF), these details are front-loaded and relevant to understanding the tool's matching behavior, though slightly overwhelming for basic usage decisions.

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 complex retrieval algorithm and lack of output schema, the description adequately explains the matching methodology but omits description of return values (e.g., similarity scores, ranked list structure). The include_details parameter hints at output capabilities (common patterns/differences), but explicit return documentation would improve completeness.

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 description coverage, the schema fully documents all parameters (URL existence requirement, limit range 1-20, include_details boolean). The description focuses on algorithmic internals rather than parameter semantics, which is acceptable given the comprehensive schema documentation.

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?

Description explicitly states the tool searches for similar website designs given a URL input, using specific technical verbs (検索/searches, 生成/generates, 発見/finds). The detailed algorithm description (DINOv2 vision + e5-base text embeddings) clearly distinguishes this from siblings like design.search_by_image or design.compare.

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?

While the description specifies URL input and implies the requirement for the URL to exist in the database (via the embedding generation explanation), it lacks explicit guidance on when to use this tool versus alternatives like design.search_by_image or layout.search. The constraint that URLs must exist in DB is only in the schema, not the main description.

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