Start network capture

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

With no annotations, the description carries full burden and excels. It discloses the underlying mechanisms (OkHttp Frida hook, mitmproxy routing, CA trust), the side effect on macOS proxy and its restoration on stop, and the meaning of the filter regex. This is exemplary transparency beyond what annotations could provide.

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 two dense sentences, front-loaded with the primary action. It structure clearly separates general purpose from platform details, with no wasted words.

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?

Given the tool's complexity (platform differences, prerequisites, side effects) and no output schema, the description is remarkably complete. It covers Android and iOS modes, requirements, filter syntax, and proxy restoration, leaving no critical operational gap.

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 coverage is 100%, so baseline is 3. The description adds value by clarifying platform-specific requirements (app_id required on Android, optional on iOS), giving a filter example ('v2/search'), and explaining the spawn parameter. These enrich the schema's already explicit descriptions.

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 'Capture decrypted HTTP, filtered to specific endpoints,' which is a specific verb+resource+scope. It clearly distinguishes from siblings like network_stop and network_mock by focusing on starting a capture with platform-specific methods.

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 clear context for when to use the tool: platform-specific prerequisites (Android requires debuggable app and frida-server; iOS uses mitmproxy) and filter semantics. It doesn't explicitly name alternatives, but the sibling names and detailed requirements make the intended use obvious.

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