connect_device

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

No annotations are provided, so the description bears the full burden of behavioral disclosure. It reveals that the tool establishes a connection and enables further device operations, but it does not disclose non-obvious behaviors such as whether it modifies the device's state, requires specific permissions, or handles errors. The absence of details about side effects or failure modes limits transparency. While not incorrect, it could be more explicit.

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 extremely concise: two short sentences in Chinese that convey the purpose and basic usage instructions. The first sentence introduces the tool's function, and the second provides parameter guidance. No unnecessary words or redundant information. This structure efficiently communicates the essential information without burdening the agent.

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?

Given that there is no output schema, the description should ideally explain what the tool returns (e.g., connection ID or success status). It does not mention return values or error handling. However, the description covers the core usage pattern and prerequisites. Sibling tools like 'get_device_status' and 'observe_device' imply that connection is a prerequisite, and the description reinforces that. The missing return value info is a minor gap but does not severely impair usability.

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 provides 100% description coverage for all four parameters, including default values and enums. The description adds marginal value by stating that the port is ignored in ADB mode and clarifying the required format for 'ip' (IP for LAN, serial for ADB). However, this is already implied by the schema's parameter descriptions. Thus, the description does not significantly enhance understanding beyond 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?

The description clearly states the tool's purpose: connecting Android/iOS devices as a prerequisite for using other device tools like screenshots and UI trees. It distinguishes the tool from siblings by specifying that it is the initial connection step, and it contrasts with tools like 'auto_connect' which might automate the process. The verb 'connect' and resource 'device' are specific and unambiguous.

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 explicitly says when to use this tool: before using device-specific tools (screenshots, control tree). It provides guidance on parameter usage: for LAN devices pass IP, for ADB pass serial number and set connection_mode='ADB'. However, it does not mention when not to use this tool or provide alternatives; the sibling list includes 'auto_connect' which may be an alternative in some scenarios.

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