get_browser_diagnostics

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

No annotations are provided, so the description carries the full burden. It discloses that data is privacy-redacted, explicitly enumerates the sensitive types never captured (headers, bodies, cookies, tokens, typed values, raw query values), and qualifies the reliability ('diagnostic lead rather than a verified assertion'). This is substantial behavioral transparency for a read-only tool, though it does not mention things like rate limits or latency.

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 exactly two sentences: the first front-loads the evidence types and scope, the second clarifies privacy and reliability. Every clause adds value without redundancy, and the structure is ideal for quick agent scanning.

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 read-only diagnostic tool with no output schema, the description adequately conveys what the tool returns (the listed evidence categories) and what it deliberately omits, which is sufficient for an agent to decide to call it. It does not specify the exact response format (e.g., array structure), but that is not essential for a tool of this nature. The reliability caveat further enriches context.

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 description coverage is 100%, so the schema already fully documents both parameters: id (recording public id or URL) and maxEvents (max failures/navigation events). The description adds no parameter-specific meaning beyond what the schema provides, so it stays at the baseline 3.

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 names a specific verb ('get'), a clearly defined resource ('privacy-redacted browser evidence captured with a recording'), and enumerates the exact categories (visited routes, console warnings/errors, page exceptions, failed fetch/XHR metadata). It also explicitly lists what is never captured, which sharply distinguishes this from other recording tools like get_transcript or get_recording.

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 makes the purpose obvious for diagnostic use and warns that evidence is 'page-reported' and should be treated as a lead rather than verified. While it does not explicitly name alternative tools or the conditions under which to prefer them, the content is specific enough that an agent can infer when to call it (e.g., when browser-side errors or failed requests are relevant). The caveat about reliability adds useful context.

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