capture_live

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 lists defaults and max values but does not disclose whether the capture stops at packet_count, duration, or whichever comes first, nor does it mention permission requirements, blocking behavior, or error handling. The 'Returns' line only says 'Captured packet summary' without detailing its contents.

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 and well-structured: a single-purpose opening line, a clearly labeled Args block, and a Returns section. Every sentence provides necessary detail with no redundancy or fluff, making it easy for an agent to parse quickly.

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?

While an output schema exists, the description misses several contextual elements for a network capture tool: when to choose this over capture_and_decrypt, the capture termination logic (packet count vs. duration), and any system-level prerequisites (e.g., admin rights). The parameter details are solid but the body of behavioral and usage context is insufficient for full confidence.

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 schema has 0% description coverage, so the description compensates by explaining each argument: interface is named and points to list_interfaces, packet_count has default and max, display_filter is described as optional, and duration has default and max. This adds meaningful context beyond the bare schema titles and defaults.

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 opens with a specific and clear statement: 'Capture live packets from a network interface.' This pinpoints the exact resource (network interface) and distinguishes it from offline analysis tools like analyze_pcap_file. The verb 'capture' is precise and action-oriented.

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 gives one practical hint: 'use list_interfaces to find names' for the interface parameter. However, it does not explicitly state when to use capture_live versus siblings like capture_and_decrypt or analyze_pcap_file, nor does it mention any exclusions or prerequisites beyond listing valid interfaces.

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