start_live_capture

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

With no annotations, the description carries the full burden. It discloses the return value (capture_id) and the adopt vs. start distinction ('without clearing it'), but omits behavioral details for reset_session/include_existing, session lifecycle, and what 'Charles' refers to.

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?

Three sentences with zero waste: purpose front-loaded, return value stated, and specific parameter usage included. Every sentence earns its place with no redundancy.

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?

Adequate for a session initialization tool with an output schema (which handles return documentation), but gaps remain: two parameters lack semantic explanation, and the 'Charles' ecosystem context is only mentioned in passing.

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 has 0% description coverage (only titles). The description compensates by explaining adopt_existing behavior, but leaves reset_session and include_existing completely undocumented with no indication of their effects or default behaviors.

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 states the tool starts or adopts a live capture session for incremental polling, explicitly mentions it returns a capture_id required by all other live tools, and distinguishes itself as the entry point for the live capture workflow versus recorded traffic siblings.

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?

Provides specific guidance on using adopt_existing=true to take over sessions without clearing them, and implies this must be called first for live workflows. However, lacks explicit when-not-to-use guidance or comparison to alternatives like analyze_recorded_traffic.

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