ReftrixMCP

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

Annotations declare readOnlyHint=true and idempotentHint=true. The description adds valuable behavioral context beyond these: it specifies the output scale (0-1 scores) and explains what include_details actually returns (common patterns and key differences). No contradictions with annotations.

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?

Perfectly structured bilingual description. First sentence delivers core functionality (comparison dimensions and scoring), second sentence explains the optional details flag. Zero waste, front-loaded with essential information, appropriate length for complexity.

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?

No output schema exists, but the description adequately covers the return value concept (pairwise scores 0-1, optional pattern details). Given the tool's focused scope (comparison only) and strong annotations, the description provides sufficient context for invocation, though exact response structure could be detailed further.

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 meaningful semantics by explaining the functional impact of include_details (what 'details' means: common patterns and differences) and reinforcing the cardinality constraint (2-5 pages). This goes beyond the schema's boolean flag description.

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 specific action (compare), resource (2-5 web pages), methodology (4 axes: layout, visual, quality, color), and output (pairwise similarity scores 0-1). It distinguishes from siblings like design.search_by_image (search by image) and design.track_changes (temporal tracking) by specifying direct pairwise comparison of specific page IDs.

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 implies prerequisites by specifying UUID format for page_ids, suggesting pages must be ingested first. However, it lacks explicit when-not-to-use guidance or named alternatives (e.g., 'use design.similar_site for finding similar sites by URL instead'). Usage context is present but implied rather than explicit.

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