rubrkit_read_input_driftCompare recent production inputs against a prior reference window (population stability index) for an artifact bundle via GET /api/v1/artifact-bundles/{artifactBundleId}/drift/input. Requires artifact_bundles:read (or artifacts:pull) for API keys.
| Name | Required | Description | Default |
|---|---|---|---|
| binCount | No | ||
| windowDays | No | ||
| artifactBundleId | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description must fully disclose behavioral traits. It implies a read operation (via 'Compare' and required read permissions) but does not explicitly state idempotency, side effects, rate limits, or data retrieval characteristics. The endpoint URL adds structural detail but not behavioral transparency.
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 description is concise at two sentences. The first sentence efficiently conveys action, method, and endpoint; the second covers permission requirements. No redundant text, though the first sentence is dense.
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 no annotations, no output schema, and incomplete parameter explanations, the description is insufficient for reliable tool selection and invocation. Missing details include return format, error handling, parameter constraints, and behavior beyond the basic operation.
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?
The input schema has three parameters (artifactBundleId, binCount, windowDays) with 0% schema description coverage. The description only mentions artifactBundleId implicitly via the endpoint and hints at windowDays ('reference window'), but entirely omits binCount. The agent lacks essential meaning for binCount.
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 identifies the specific action: compare recent production inputs against a prior reference window using population stability index (PSI) for an artifact bundle. It includes the exact HTTP method and endpoint path, distinguishing it from sibling tools like read_drift_observations and read_validity_drift.
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 lists required permissions (artifact_bundles:read or artifacts:pull), providing practical guidance. However, it does not explicitly contrast with other drift-related sibling tools or state when to prefer this over alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools target distinct resource-action pairs, and descriptions clarify differences like soft vs hard delete or list bundles vs list versions. However, some names are similar (e.g., delete_artifact_bundle vs hard_delete_artifact_bundle), which could cause minor confusion.
All tools follow a uniform rubrkit_verb_noun pattern with imperative verbs and snake_case, making them predictable and easy to navigate. No mixed conventions or inconsistencies.
With 30 tools, the server is comprehensive but slightly heavy for a single-purpose MCP. The tools cover multiple sub-domains (bundles, files, audits, evals, conversions, docs), which justifies the count, but consolidation could reduce complexity.
The set covers CRUD for artifact bundles, file operations, audit/eval lifecycle, and API documentation. Minor gaps include missing bundle metadata update and file deletion, but core workflows are supported.