Record traffic

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

No annotations are supplied, so the description carries the full behavioral burden. It does disclose that capture happens inside the browser where pages cannot see it, that the files contain cookies and page-sent data, and that 'full' retains compiled scripts. However, it omits whether a browser must be running, what happens if a recording is already active, and how the recording terminates besides the timer. For a capture tool with zero annotation coverage this leaves meaningful gaps.

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, front-loaded with what is captured before the caveats. The nested parentheticals and colon-separated lists make it slightly dense, but no sentence is wasted and the security warning is placed last where it reads as a caveat rather than the headline.

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?

With no output schema, the description usefully characterizes the return artifacts (HAR, request list, summary) and the extra output of 'full'. Still missing is the operational context an agent needs: prerequisite browser state, the pairing with record_stop, and whether repeated starts are allowed. Adequate but incomplete for a recording 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 67%, so the schema already documents path and minutes. The description adds real meaning for the level enum by explaining that 'full' additionally keeps every script the pages compiled, but it says nothing about how the default 'network' level differs in output or how path interacts with the default recordings/ folder beyond what the schema states.

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 a concrete verb and resource ('Records every request, response and websocket message of the whole browser') and enumerates the artifacts produced (HAR with bodies, grep-able request list, summary). It is clearly distinct from siblings like screenshot or observe, though it never names record_stop, the natural counterpart.

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?

There is no explicit when-to-use statement, no mention that a browser session must already be open, and no reference to stopping the recording with record_stop. Usage is only implied by the tool name and the phrase 'from inside the browser'. An agent must infer the whole workflow.

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