ReftrixMCP

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

Annotations indicate readOnlyHint: false and idempotentHint: false. The description adds valuable behavioral context not found in annotations: it clarifies the conditional mutation behavior (only updates when feedback is present) and distinguishes between sample retrieval vs profile mutation modes. Does not mention side effects like profile creation when profile_id is omitted.

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?

Extremely efficient bilingual format (Japanese/English) with zero redundancy. Two sentences cover concept and mechanics. First sentence establishes the domain (preference hearing), second explains the conditional logic. Every word 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 6-parameter mutation tool with no output schema, the description adequately covers the core interaction model (dual modes) and hints at return behavior ('present samples'). However, it could explicitly describe the return structure or pagination behavior given the limit/offset parameters exist.

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 baseline is 3. The description adds conceptual meaning beyond the schema by explaining the semantic relationship between the feedback parameter and the tool's behavior mode (feedback presence triggers profile updates). It provides the 'why' for the feedback array parameter.

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 explicitly states the dual-purpose nature: 'present samples without feedback, update profile with feedback.' It uses specific verbs (present/update) and clearly distinguishes from sibling tools like preference.get (retrieval) and preference.reset by defining this as an interactive 'hearing session' that modifies state.

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?

Provides clear context for the two operational modes (Mode A: sampling without feedback, Mode B: updating with feedback), which effectively guides when to include the feedback parameter. Lacks explicit naming of alternatives like preference.get for read-only access, though the distinction is implied by the 'hearing' concept.

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