ReftrixMCP

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

Beyond annotations (readOnlyHint: false, indicating state mutation), the description adds valuable behavioral context: it discloses the embedding diff methodology, explains the 0-1 change score semantics (0=identical, 1=completely different), and details the four section-level change categories (added/removed/modified/unchanged). This effectively compensates for the lack of output schema by explaining what the user can expect from the tool's analysis.

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 (Japanese/English) efficiently serves dual locales without redundancy. The description is front-loaded with the core purpose, followed by action enumeration and output semantics. Every sentence conveys essential information about capabilities, methodology, or return values, though the density of the bilingual format slightly impacts readability.

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?

Despite having no output schema, the description comprehensively explains the return semantics through the change score (0-1) and categorical change classifications (added/removed/modified/unchanged). It adequately covers the complexity of the four-mode tool (snapshot/compare/history/detect) and their distinct behaviors, providing sufficient context for an agent to select appropriate actions based on user intent.

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 itself fully documents all five parameters including the action enum and conditional fields (snapshot_ids for compare, limit for history). The description reinforces the four action types but does not add significant semantic detail beyond what the structured schema already provides, which is appropriate given the high schema coverage.

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 tracks design changes for the same URL over time (時系列で追跡/Tracks design changes of the same URL over time). It explicitly enumerates the four distinct actions provided (snapshot, compare, history, detect) and distinguishes itself from siblings like design.compare by emphasizing temporal tracking of identical URLs versus cross-site comparison.

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 workflow context by referencing page.analyze in the auto_snapshot parameter description (page.analyze後の自動スナップショット), suggesting integration with that sibling tool. While it doesn't explicitly list when *not* to use the tool, the specific focus on '同一URL' (same URL) tracking provides sufficient implicit guidance to differentiate it from alternatives like design.compare or design.search_by_image.

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