ReftrixMCP

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

Annotations declare readOnlyHint and idempotentHint. The description adds valuable behavioral context not in annotations: it discloses the internal parallel execution model and similarity-score merging logic. It does not contradict annotations (searching/merging aligns with read-only). Could improve by mentioning latency implications of parallel execution or cache behavior.

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?

Despite being bilingual (Japanese/English), the description is extremely efficient: two sentences per language with zero waste. First sentence establishes scope (five domains), second explains mechanism (parallel execution + merge). Information is front-loaded and every clause earns its place.

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 complex 12-parameter cross-domain tool, the description provides sufficient high-level context given the rich annotations and complete schema. It explains the merging behavior adequately. Minor gap: no output schema exists, and the description doesn't detail return structure (e.g., whether it returns unified objects or typed collections), though it implies similarity-scored results.

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 12 parameters including the five type enums. The description mentions the five component types (layout, part, motion, background, narrative) which reinforces the 'types' parameter semantics, but does not need to duplicate the comprehensive schema documentation. Baseline 3 is appropriate given schema completeness.

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 precisely defines the tool's scope using specific verbs ('cross-component semantic search') and enumerates all five searchable domains (Layout, Part, Motion, Background, Narrative). It clearly distinguishes this as an aggregator that 'executes individual search tools in parallel,' differentiating it from sibling single-domain tools like layout.search or part.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 implies usage context by stating it executes individual search tools in parallel and merges results, suggesting this is for cross-cutting queries rather than single-domain searches. However, it lacks explicit 'when to use unified vs. specific tools' guidance (e.g., 'use this when searching across multiple component types, use layout.search for layout-only queries').

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