capture_packets

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states that it captures live traffic and returns JSON, but does not disclose prerequisites (e.g., root/admin privileges, tshark installed), side effects (e.g., network interface impact, potential data volume), or termination behavior (e.g., duration-bound). These are significant gaps for a capture tool.

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 concise, fitting in one sentence plus a short list. The Chinese prefix '【实时抓包】' is somewhat redundant but not harmful. The use-case list is efficient and front-loaded. Overall, it is well-structured and not wordy.

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?

The tool has 3 parameters (all documented in schema), no output schema, and no annotations. The description gives a high-level return format ('raw packet data as JSON') and use cases, but does not detail the capture lifecycle, how raw data is structured, or how this differs from run_tshark, which is a sibling. It is minimally sufficient but leaves gaps for a network operation.

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 100%, since each parameter (duration, interface, tshark_path) has a description in the input schema. The description text adds little beyond the schema, only implicitly referencing duration via 'capture live traffic', so the baseline of 3 is appropriate.

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 uses a specific verb ('Capture') and resource ('live traffic') and specifies the output format ('raw packet data as JSON'). It clearly distinguishes itself from sibling tools like list_pcaps and load_pcap, which handle existing captures, while this tool is for live capture.

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 provides 'Use this when' conditions (live traffic capture, monitoring, real-time threat detection), which gives clear context for when to select the tool. It does not mention when not to use it or mention alternatives, but the stated use cases are sufficient for basic guidance.

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