start_capture

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

With no annotations provided, the description carries the full burden. It discloses a critical behavioral guarantee: the capture is always bounded by both duration_s and max_packets, which implies the capture will terminate under those conditions. However, it does not describe whether the call blocks, returns immediately, or yields a capture handle, nor does it mention permissions or side effects beyond starting a capture. The single disclosed trait is useful but incomplete.

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—and front-loaded with the action verb. There is zero fluff or redundancy. While it may be too terse for the tool's complexity, the conciseness itself is commendable; every word earns its place. It loses a point because it omits necessary detail rather than achieving brevity through efficient wording.

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 four parameters, no schema descriptions, no annotations, and no output schema, the description is far too thin. It lacks essential context: what the interface parameter expects, how to specify a BPF filter, what happens after capture starts (e.g., how to reference it with sibling tools like capture_info or follow_stream), and whether a capture ID is returned. The 'bounded' clause is helpful but does not cover the operational workflow. An agent cannot confidently use this tool without external knowledge.

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 0%, so the description must compensate. It mentions only duration_s and max_packets (as bounding constraints) but provides no meaning for the required parameter 'interface' or optional 'bpf_filter'. It does not clarify units, limits, or how max_packets interacts with duration_s beyond the 'both' clause. This is insufficient for an agent to correctly set parameters without additional inference.

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 states a specific verb ('Capture') and resource ('live packets on an interface'), making the tool's function unambiguous. It also adds a distinctive scope constraint ('Always bounded by BOTH duration_s and max_packets') that differentiates it from sibling tools like list_captures or packet_summary, which are not about starting a 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 provides no guidance on when to use this tool vs. siblings. It does not mention prerequisites (e.g., selecting a valid interface via list_interfaces), when not to use it, or how the capture results are retrieved (e.g., via list_captures). The 'Always bounded' clause offers a runtime constraint but not usage context.

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