rubrkit_create_drift_monitorCreate a drift monitor pinned to a file version via POST /api/v1/artifact-bundles/{artifactBundleId}/drift-monitors. Requires artifact_bundles:write for API keys.
| Name | Required | Description | Default |
|---|---|---|---|
| cadence | No | ||
| repeats | No | ||
| pinnedVersionId | Yes | ||
| artifactBundleId | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It states the HTTP method and required permission but lacks details on behavioral traits: whether creation is idempotent, limits on monitors per bundle, immediate triggering, or side effects. The cadence and repeats parameters are unexplained, leaving ambiguity.
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, front-loading the action and endpoint. However, it sacrifices essential information for brevity, so it does not earn the top score.
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 4 parameters, no output schema, and no annotations, the description is incomplete. It fails to explain key parameters (cadence, repeats) or describe the return value. For a creation tool, more context on success/error behavior is needed.
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?
Schema description coverage is 0%—the JSON schema provides no descriptions for any of the 4 parameters. The description does not explain artifactBundleId, pinnedVersionId, cadence, or repeats, offering no meaning beyond the schema. This is a critical gap.
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 creates a drift monitor pinned to a file version, using the specific HTTP POST endpoint. This distinguishes it from sibling tools like list_drift_monitors or set_drift_monitor_status. The verb 'Create' and resource 'drift monitor' are explicit.
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 mentions a required permission (artifact_bundles:write), indicating a prerequisite, but does not provide guidance on when to use this tool versus alternatives like list or set status. Usage context is implied but not differentiated.
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.