Start a frontend bug investigation

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

Goes well beyond annotations: discloses the execution sandbox ('isolated, policy-restricted Chromium context'), enumerates the evidence channels recorded, states the return value, and flags that page-derived text is untrusted and must not be followed as instructions. The annotations only say openWorld/non-idempotent/non-destructive; the prompt-injection warning is a genuinely high-value disclosure that annotations cannot convey.

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 tight sentences, front-loaded with what the tool does, then the return value, then the configuration hint, then a security caveat. Every sentence carries distinct information with no filler.

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 8 parameters including nested objects, plus an output schema and annotations, the description covers action, scope, return, and safety. What's missing is lifecycle guidance — duration/blocking behavior and the expected next step (e.g., collect_evidence) for an investigation-started session.

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 75%, so the baseline is 3. The description's selector advice largely restates the schema's own 'watch' description ('needed to observe flicker and placeholder bugs'), and undocumented items like the waitUntil enum values, viewport, and maxDurationSeconds semantics get no added explanation.

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?

States a concrete verb and resource: opens targetUrl in an isolated, policy-restricted Chromium context and begins recording named evidence channels. The addition of 'Returns an investigation id' and the selector guidance make it clearly distinguishable from collect_evidence or reproduce_issue, though the description never names those siblings explicitly.

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?

'Use watch.loading / watch.content selectors for flicker or placeholder bugs' is real conditional guidance, but it only covers one parameter's configuration. There is no statement of when to call this instead of reproduce_issue, collect_evidence, or what prerequisite state is needed.

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