Diagnose

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

With no annotations provided, the description carries the full burden and does an excellent job: it discloses deterministic rule-based behavior, no fabrication, automatic frame extraction from logs, network probing from host+port, sorted candidates, preservation of raw observations, and empty candidates when the knowledge base does not cover the case. This is substantial behavioral disclosure beyond the bare tool name.

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 front-loaded with the core purpose, uses a bullet list for evidence modes, and every sentence carries information. It is dense but not bloated, with no filler.

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 tool with no annotations and 0% schema coverage, it covers the essential input modes, output contract, and behavior meaningfully, and the presence of an output schema reduces the need to describe return fields. The main missing piece is the required protocol/unit semantics and an explicit pointer to list_protocols or a list of supported values.

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 description adds useful semantics for frame_hex, log_snippet, host, and port, including parse/checksum, automatic frame extraction, and probing behavior. But the schema coverage is 0% and the required protocol parameter is left completely unexplained, as is unit; an agent would have to guess or look elsewhere for valid protocol values.

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 identifies the tool as one that maps observations to structured fault candidates and specifies the output report. The verb 'diagnose' plus resource ('故障候选结论') is concrete, but it does not explicitly differentiate from sibling tools such as parse_frame or probe_device, so it stops short of full sibling differentiation.

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?

It gives explicit input constraints: any combination of frame_hex, log_snippet, or host+port, with at least one required. However, it never states when to choose diagnose over the sibling parsing/probing/listening tools or names an alternative, so the agent must infer the intended entry point.

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