Roll back a device's configuration to a specified earlier version. Initiates the rollback and returns a job ID for tracking progress.
Trigger a rollback of a device to a prior configuration version. Returns a job id; poll sdcloud_get_config_rollback_status for progress.
| Name | Required | Description | Default |
|---|---|---|---|
| device_uuid | Yes | ||
| version_number | Yes |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It discloses that the operation returns a job id and is asynchronous, requiring polling. However, it does not mention potential side effects (e.g., device downtime), required permissions, or error conditions (e.g., invalid version_number). The description is minimal but not misleading.
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?
Two concise sentences that front-load the purpose and then provide the next steps. Every sentence adds value without any fluff or repetition.
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 that this is an asynchronous rollback operation with no output schema, the description should explain the return value format (just says 'job id') and any prerequisites (e.g., device must exist, version must be a valid prior version). It references the status polling tool, which helps, but misses important details like error handling or version validation.
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 two parameters (device_uuid, version_number) with no descriptions (0% schema_description_coverage). The description does not explain these parameters at all, leaving the agent to guess their meaning or format. For example, it does not specify that version_number likely comes from sdcloud_list_device_config_versions. This is a significant 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's purpose: 'Trigger a rollback of a device to a prior configuration version.' The verb (trigger rollback) and resource (device configuration version) are specific, and it is easily distinguishable from sibling tools like sdcloud_get_device_config_latest_version or sdcloud_list_device_config_versions.
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 explicit guidance on what to do after calling the tool: 'Returns a job id; poll sdcloud_get_config_rollback_status for progress.' This tells the agent to use the status-pulling sibling tool. However, it does not mention when to use this tool versus alternative rollback methods, but for a simple rollback operation, the guidance is adequate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.