Start rotation

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

The description goes well beyond the annotations. It discloses that the tool is a mutating operation (readOnlyHint=false), but also that it is idempotent (idempotentHint=true) by explicitly stating 'Calling it again replaces the schedule'. It also adds important behavioral details: the requirement for a control-scope token and a Portveil-agent device, and that the schedule runs independently of the assistant. This is valuable context not captured in annotations.

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 four sentences long, each adding essential information: the core action, the autonomy of the scheduler, the replaceable nature, and the stopping mechanism plus requirements. It is front-loaded with the primary purpose and contains no filler or redundant phrasing. Every sentence earns its place, making it highly concise and well-structured.

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 tool with three parameters, no output schema, and relatively simple behavior, the description covers the essential context: purpose, scheduling behavior, replacement semantics, stopping, and prerequisite requirements. It does not detail error handling or what happens with invalid inputs, but these are minor gaps. The description is complete enough for an agent to correctly invoke the tool in most scenarios, though it could optionally mention the distinction from immediate move tools.

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 already provides comprehensive descriptions for all three parameters (device, locations, every_minutes), with 100% coverage. The tool description does not add additional parameter-specific meaning beyond what the schema provides. For example, the schema already explains the range for every_minutes and the optional nature of locations. Therefore, the description adds no extra semantic value for parameters, matching the baseline of 3.

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 function: 'Make Portveil move a device to the next location automatically every N minutes'. It specifies the verb (move), resource (device), and the automation aspect (every N minutes). It also distinguishes itself by mentioning 'Calling it again replaces the schedule' and 'Stop it with stop_rotation', which sets it apart from immediate move tools. The purpose is unambiguous.

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 clear context on when to use the tool: for scheduling periodic moves. It explains that Portveil runs the schedule itself, so the assistant doesn't need to stay running, and that calling again replaces the schedule. It also names stop_rotation as the way to stop. However, it does not explicitly contrast with sibling tools like rotate_device or move_device, leaving some ambiguity for an agent choosing between them. Thus, it has clear context but lacks explicit exclusions or alternatives.

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