dreame_control

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

There are no annotations, so the description carries the burden of explaining side effects. It does this well by showing that it starts/stops cleaning, returns the robot to dock, drives it, exports maps, clears errors, and reports status. It lacks explicit safety, authorization, failure, or real-world movement caveats, which would be needed for a 5 given the lack of 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 dense but appropriately sized for 16 operations. It front-loads the tool’s authoritative use case and then gives a clear, ordered list of operation behaviors. Every line earns its place and there is no filler.

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 complex tool with 15 parameters and 16 operations, the description is broadly complete: it explains each operation's domain and the main output categories. The output schema and the schema-level parameter descriptions remove much of the burden. However, it does not state required argument conditions, such as when `clean_zone` needs `zones` or `move` needs `rotation` and `velocity`, so those constraints remain inference rather than explicit guidance.

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 covers 87% of the parameters, so the baseline is 3. Description does add meaningful context beyond the schema by mapping values like suction 1-4, water 1-3, and mop humidity 1-3, but most of the parameter meaning is already in the schema and the description does not explain conditional parameter requirements between operations.

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 first sentence clearly names a specific resource, the Dreame D20 Pro vacuum, and a specific action domain: control. The operation list makes the scope concrete and distinguishes it from general robot/drone tools, but it does not explicitly differentiate this from the close sibling `dreame_onboard`, and much of the operation list repeats what the `operation` enum already exposes.

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 establishes a clear context: use this as the unified interface for Dreame vacuum status, cleaning, mapping, and settings operations. It does not explicitly state when not to use it or name alternatives like `robot_control` or `dreame_onboard`, so exclusion logic is left to inference.

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