capture_network

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

No annotations are provided, so the description carries the full burden. It explains it captures during page load and returns a summary, but doesn't state side effects (e.g., page navigation, state changes) or permissions needed. For a capture tool, it's likely read-only, but not explicitly said.

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 sentences, front-loaded with the core purpose. The first sentence is somewhat long but packs information efficiently. A minor improvement would be to split it for readability.

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 no output schema, the description mentions the summary output (total requests, failed, size, breakdown). It covers common use cases and explains the tool's nature (free, within Claude Code). It doesn't detail pagination or filtering but is fairly complete for a network request capture tool.

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% as both parameters (url, waitMs) have descriptions in the schema. The description adds no extra meaning beyond what the schema provides, so baseline 3 is appropriate.

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 captures network requests during page load, listing specific details (status codes, sizes, timing, resource types) and provides a summary. It distinguishes from sibling tools like capture_console or capture_errors by focusing on network-level data.

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 says it's useful for finding failed API calls, slow requests, etc., giving good usage context. It notes the tool is free and runs within Claude Code, but doesn't explicitly exclude alternatives or mention when not to use it. Sibling tools like performance_audit exist but no direct comparison is made.

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