metro_network

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

With no annotations, the description fully discloses key behaviors: auto-discovery, request/response pairing by requestId, redaction of sensitive headers by default, and format differences. It warns about not committing unredacted HAR. Missing details on rate limits or what happens if no app is connected.

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 somewhat long but well-structured with front-loaded core purpose. Every sentence adds value: pairing, format, redaction, save. Could be slightly more concise, but information density is high.

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 complexity (7 parameters, no output schema, no annotations), the description covers all parameters meaningfully, explains output (HAR-lite), and includes safety warnings. It lacks detailed structure of 'json' output but mentions method, url, status, headers, timing, which is sufficient.

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 substantial meaning beyond the schema: explains auto-discovery for webSocketDebuggerUrl, defaults for port/duration/maxEntries, that format 'har' emits HAR-lite, redact default true, and saveTo for writing files. This enriches understanding significantly.

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 'Captures network requests from a React Native app via the Metro CDP debugger (Network domain)', specifying the action and resource. It distinguishes from siblings like metro_apps (list apps) and webview_network (webview context), as seen in the sibling list.

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 clear usage context: auto-discovery when webSocketDebuggerUrl omitted, pairing of requests, format options, and a warning not to commit unredacted HAR. However, it does not explicitly mention when not to use this tool versus alternatives like webview_network.

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