browser_network_log

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

With no annotations, the description carries the full burden of behavioral disclosure. It only says 'monitor' without explaining the start/stop/get lifecycle, whether requests are logged persistently, whether it is per-tab or global, or if any side effects occur (e.g., altering request headers). This leaves critical behavioral traits undisclosed for an agent that must invoke start/stop/get actions.

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 a single, front-loaded sentence that immediately conveys the core purpose. It is efficient and avoids unnecessary words. However, it may be too sparse for a tool with multiple actions and a filter, making it slightly under-specified, though it still earns its place as a concise summary.

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 has three actions (start, stop, get), a filter parameter, no annotations, and no output schema, the description is far from complete. It leaves out expected return values, how to use the filter, whether monitoring is browser-wide or tab-specific, and potential interactions with other browser tools. An agent would lack critical information for correct invocation, especially for the 'get' action which implies reading collected data.

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% because both parameters (action and filter) have descriptions, but those descriptions are minimal ('Action' and 'Filter by URL'). The tool description adds no extra semantics, such as how the filter interacts with each action or whether filter is used during start or retrieval. The baseline of 3 is appropriate since the schema already documents the parameters adequately, but no additional meaning is provided.

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 uses the specific verb 'monitor' and identifies the resource as 'fetch/XHR network requests', making it clear what the tool observes. It is distinct from sibling tools like browser_get_console_logs, which handle console output rather than network activity. No ambiguity or tautology; it communicates the core function effectively.

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?

No guidance is provided on when to use this tool versus alternatives, nor any exclusions or prerequisites. The description does not hint at typical use cases (e.g., debugging API calls, tracking performance) or contrast with logging or console tools. It simply states what it does without context for decision-making.

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