auto_discover

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

With no annotations, the description carries the full burden and does so thoroughly. It discloses the exact network addresses (192.168.16.254:8080 and 192.168.1.255:8080), the multi-NIC matching behavior, the step-by-step process (connect → broadcast search → query IO/modules → register device), and the failure handling. This goes well beyond a basic statement of function and gives the agent a clear model of side effects and edge cases.

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 paragraph but well-organized: it starts with the purpose and prerequisite, then details each connection type, then the flow, then the fallback. Every sentence carries substantive information, though it could be improved with bullet points for scanability. It is not overlong for the complexity covered.

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 the tool's complexity (network/serial discovery, multi-step process) and the absence of an output schema, the description covers all major behavioral aspects: the prerequisite question, serial/network variants, exact addresses, the automated sequence, and failure escalation. It does not explicitly state the return value or success result, but the outcome (device registration) is implicit, leaving only minor gaps.

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 coverage is 100% with descriptions for all parameters, so the baseline is 3. The description adds significant value by providing concrete values for connection_type behavior (e.g., the actual IP/port and the default baud rate of 9600) and clarifying that path is required only for serial, enhancing the schema's abstract descriptions without being redundant.

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 "设备搜索与添加" (device search and add), specifying both the action (search and add) and the resource (devices). It also distinguishes itself from sibling tools by outlining the auto-discovery workflow and explicitly referencing setup_connection for manual fallback, making it unmistakable when this tool is the right choice.

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?

Provides explicit trigger conditions: when the user says "搜索设备" the AI must first ask the connection method and then call this tool. It also details the behavior for both network and serial modes, and instructs that if default addresses fail, the user should confirm the actual address and use setup_connection manually, thereby covering when-to-use and alternative tools.

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