control

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

With no annotations, the description carries the full burden of behavioral disclosure. It provides no information about side effects, permissions, whether operations are reversible, what happens on failure, or what the tool returns. 'Paired control' hints at a relationship with observe but is too opaque to inform an agent about consequences.

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 brief and front-loaded, but it is under-specified rather than effectively concise. Both sentences are short, but the second is cryptic and the first adds little actionable meaning.

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?

Despite the presence of an output schema, the description lacks essential context for a tool with three parameters and no annotations. An agent cannot determine when to use it, what each operation entails, how to construct parameters, or what behavior to expect. This is not enough for correct invocation.

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% and the description does not explain device, value, or any operation besides press. The agent is left without guidance for what value means, how to specify a device, or how operations like transport or open_url should be formatted.

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 only "Paired control" and gives a navigation hint, but never explicitly states that the tool performs device control operations such as wake, sleep, transport, press, open_url, launch, or type. The resource and overall verb are left to inference from the schema, so the purpose remains vague.

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 sentence 'Use press for explicit buttons; observe agent-chosen navigation' gives one concrete usage rule: choose press when an explicit button should be pressed, and use observe for navigation decisions. However, it does not explain when to use control vs. sibling tools like act, status, or apps, or how to select among the other operations.

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