Start a Roborock vacuum cleaning the whole home or resume a paused clean; pass room names to clean only selected rooms.
Start cleaning. Without rooms: the whole home (or resume a paused cleaning).
With rooms: only those rooms, by the names used in the Roborock app. Get duid from list_devices.
| Name | Required | Description | Default |
|---|---|---|---|
| duid | Yes | ||
| rooms | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only declare readOnlyHint=false and destructiveHint=false; the description adds meaningful behavior beyond that, notably that an empty `rooms` resumes a paused cleaning — a non-obvious side effect an agent needs. It also discloses the naming contract for rooms (must match Roborock app names), which prevents failed calls. It does not describe behavior when a clean is already in progress or how errors surface.
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?
Three short sentences, front-loaded with the verb, then the two mode branches, then the prerequisite. Nothing is redundant and no sentence could be dropped without losing information.
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 two-parameter mutation tool with an output schema (so return values need not be explained) and non-destructive annotations, the description covers mode selection, parameter sourcing, and naming format. Only edge-case behavior (already cleaning, invalid room name) is left unspecified, which is a minor gap.
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 coverage is 0% — the schema only gives titles — so the description carries the full burden, and it does: `duid` must come from `list_devices`, and `rooms` is a set of room names as spelled in the Roborock app. Both of the two parameters gain actionable meaning not present in the schema.
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?
States a specific verb and resource ('Start cleaning') and immediately splits the behavior into two clearly described modes: full-home/resume with no `rooms`, versus room-scoped cleaning with `rooms`. It does not explicitly name or contrast the sibling `pause_cleaning`/`return_to_dock`, but the operation is unambiguous on its own.
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?
Gives explicit conditional guidance: omit `rooms` for the whole home or to resume a paused cleaning, supply `rooms` for targeted cleaning. It also routes the agent to `list_devices` for the required `duid`, which is real cross-tool guidance. No exclusion such as 'do not call while already running' is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.