Attach Raw CDP

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

With no annotations present, the description carries the burden of disclosing behavior. It transparently warns that 'captured Raw events may expose credentials and private data,' which is critical for an unrestricted CDP session. It also implies the session is full-access ('unrestricted') and mentions a 'sanitized network projection' when captureEvents=false, adding useful caveats beyond the schema.

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: the first states the primary purpose, the second gives a critical usage tip. Every word adds value, and it is front-loaded with the action and scope. No filler or repetition of schema details.

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?

For an attach tool, the description covers the key risk (exposure of private data), the main mode (raw events vs. sanitized projection), and the unrestricted nature. It does not describe the return value, but given there is no output schema and this is a session-setup tool, the provided warnings and parameter guidance give enough context for safe use. A small gap is the lack of explicit mention that a separate session ID is returned, but this is inferable.

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?

The input schema has 0% description coverage, and the description only partially explains captureEvents by linking it to the security tradeoff. tabId, maxBytes, and maxEvents are not described in the text, leaving the agent to infer their meaning from names alone. This fails to compensate for the absent schema 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 starts with a specific verb 'Attach' and names the resource ('unrestricted Chrome DevTools Protocol session to one tab'), clearly distinguishing this from sibling tools like browser_cdp_send, which sends commands, and browser_cdp_detach, which removes a session. The mention of 'unrestricted' conveys the tool's scope of power, making its purpose unmistakable.

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 actionable guidance: 'Set captureEvents=false when only commands plus a sanitized network projection are needed,' which helps the agent choose parameter values based on the use case. It does not explicitly contrast this tool with alternatives (e.g., browser_cdp_send), but the conditional recommendation is clear context for when to reduce event capture.

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