Power Bluetooth on/off

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

With no annotations provided, the description carries the full burden for behavioral disclosure. It mentions 'persistent rfkill-aware' and 'verify the adapter state,' which hints at using rfkill and checking state, but does not explain side effects (e.g., whether this disconnects active devices, requires root privileges, or what happens if the adapter is already in the requested state). It also does not indicate whether the command is blocking or asynchronous. This is thin coverage for a state-changing operation.

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 a single concise sentence with no filler. It front-loads the key information: the command is persistent, rfkill-aware, and verifies state. Every word contributes meaning, and there is no redundant phrasing.

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 simple toggle with a single enum parameter, the description covers the core action, but it omits details that would help an agent anticipate results: what the tool returns (e.g., success status, new state), error conditions (e.g., adapter not present), and whether it affects ongoing connections. The mention of 'verify the adapter state' hints at a return value, but it is not explicit. Given the low parameter count and lack of output schema, a complete description should specify the return format and potential failures.

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 only parameter is 'state' with an enum of on/off, which is self-explanatory. The schema already defines the allowed values, and the parameter name makes the intent clear. However, schema_description_coverage is 0%, and the description does not explicitly map 'on' to enable and 'off' to disable. Since the enum is obvious, the description adds little value, but it does not hinder understanding. A score of 3 reflects that the schema covers the semantics adequately, and the description doesn't need to add much.

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 says 'Bluetooth power command' but doesn't explicitly state that it turns Bluetooth on or off. The tool name and title provide this context, but the description alone is somewhat vague. It clearly references Bluetooth power and mentions 'verify the adapter state,' which suggests a state-change operation. It distinguishes from siblings like bluetooth_status (read-only) and bluetooth_connect (connection management), though it doesn't name them. Overall, the purpose is clear enough but could be more 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?

No guidance is provided on when to use this tool vs. alternatives such as bluetooth_status or bluetooth_connect. The description does not mention prerequisites (e.g., whether Bluetooth hardware must be present) or indicate that this is the tool for toggling power. There is no mention of when not to use it. An agent has to infer that this is the toggle tool from the name and schema.

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