expose_plugin_params

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

Annotations only declare readOnlyHint=false, destructiveHint=false, openWorldHint=false. The description adds genuine behavioral context beyond that: it selects the device and manipulates its window, and it returns computer-use steps the agent must then execute — i.e. it is a preparatory UI-driving tool, not a query. It stops short of saying whether the selection/window state is restored afterward.

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?

One tight sentence, front-loaded with the purpose and immediately followed by the trigger condition and the enumerated steps. No filler. It is dense rather than wasteful, though it could be split for scannability.

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?

An output schema exists, so return-value shape need not be explained, and the trigger condition is well covered. However, for a four-parameter orchestration tool with zero schema descriptions, the omission of `track_type` and the ambiguity of `parameters` leave an agent able to misfire on half the inputs.

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 description coverage is 0% across four parameters. The description implies track_index/device_name via 'Selects the device' and gestures at 'parameters' via 'lists the exact parameter names to touch', but never clarifies whether `parameters` is an input filter or an output list, and `track_type` (defaulting to 'track') is never mentioned at all. It does not compensate for the documentation 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?

States a specific action (prepare exposing a plug-in's controls to Live) and enumerates the concrete sub-steps it performs: select device, find window, list parameter names, return computer-use steps. The parenthetical trigger condition ties it clearly to get_device_params, so it is distinguishable from the many other device tools. The phrasing 'prepare exposing' is slightly indirect, but the following clause resolves it.

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 an explicit activation condition: use it when get_device_params shows only 'Device On'. That is a real, checkable trigger and it names the sibling that produces it. It does not state when NOT to use it (e.g. for plug-ins whose params are already exposed), but the condition is strong enough to route the agent correctly.

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