start_packet_capture

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

No annotations are provided, so the description carries the full behavioral burden. It says nothing about what starting a capture actually does — that it runs until explicitly stopped, that it consumes device resources, what permissions or device connectivity are required, or whether concurrent captures are allowed. For a non-trivial operational action with zero annotation coverage, this is a substantial gap.

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 core sentence is front-loaded and useful, but the block is padded with a docstring-style Args section and a Returns section that largely restate the input schema and output schema. The toy doctest example ('result = await start_packet_capture(1)') adds no information beyond the schema.

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?

An output schema exists, so the Returns block is redundant rather than necessary, and the single parameter is covered. What's missing is lifecycle context for a stateful operation: the description never implies the capture keeps running after return or that stop_packet_capture must eventually be called, which is the one thing an agent most needs to know here.

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, and it largely does: capture_id is defined as the ID of an existing packet capture definition, with the two functions that produce such an ID named explicitly. It doesn't state whether IDs are per-ADOM or per-device, which leaves a small ambiguity.

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?

States a specific verb+resource ('Start a packet capture') and qualifies it as operating on an existing definition, which distinguishes it from the sibling add_packet_capture that creates a definition. It stops short of naming stop_packet_capture or get_packet_capture_status explicitly, so sibling separation is implied rather than spelled out.

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?

Gives a clear prerequisite and routing hint: the capture_id must come from list_packet_captures() or add_packet_capture(). However, it never states when NOT to use it (e.g., an already-running capture, or a device that doesn't support capture) and doesn't point to the stop/status siblings, so the agent must infer the surrounding workflow.

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