Get page exceptions

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

With no annotations provided, the description carries the full burden of disclosing side effects. It states that it 'enables Runtime' and 'consumes' exception events, which hints at state-changing behavior (turning on a domain, potentially clearing an event queue). It also mentions 'bounded' and 'unsanitized', giving some detail about the output. However, it does not explicitly state that the 'clear' parameter may wipe stored exceptions, or what 'bounded' means in practice (e.g., count or timeout).

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 with 12 words, making it efficient. It avoids fluff and gets to the point. However, the brevity causes some vagueness; phrases like 'bounded unsanitized' are compressed and not immediately understandable.

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 a tool with 4 parameters, no schema descriptions, no annotations, and no output schema, the description is notably incomplete. It does not explain the return format, the effect of each parameter, or the implications of enabling the Runtime domain (e.g., does it need to be disabled later?). It gives only a surface-level summary, which is insufficient for an agent to invoke the tool correctly in diverse scenarios.

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 schema has 0% description coverage, so the tool description must compensate. It uses words like 'consume' (relating to 'clear' maybe), 'bounded' (possibly 'timeoutMs' or a limit), and 'unsanitized' (implying raw output), but it does not explicitly map any of the four parameters ('clear', 'sessionId', 'timeoutMs', 'targetSessionId') to their roles. The description provides only weak hints, leaving the agent to guess the meaning of 'targetSessionId' and the effect of 'clear'.

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's purpose: enabling the Runtime domain, consuming raw exception events, and returning exception details. It uses a specific verb ('enable', 'consume', 'return') tied to a resource (Runtime, exception events), and it distinguishes itself from sibling tools like browser_cdp_send or debugger_get_paused_state by focusing on console exceptions. However, the phrase 'bounded unsanitized exception details' is somewhat vague.

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 offers no explicit guidance on when to use this tool versus alternatives. It does not mention any prerequisites, such as needing an active browser session or CDP connection, nor does it exclude scenarios where other tools (e.g., network_poll, debugger_wait_for_paused) would be more appropriate. The only implicit hint is that it is for retrieving runtime exceptions, but that is not enough.

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