Watch the live app

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

readOnlyHint=true is consistent with a passive capture tool. The description adds genuinely useful behavior the annotations don't cover: capture is time-boxed to a few seconds and requires the user to interact with the app during the window, which shapes how an agent should sequence the call.

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?

Two sentences, front-loaded with what is captured and returned, followed by the one operational instruction that matters. Nothing is redundant.

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 compensates by naming the three categories of returned data. It leaves out volume/truncation behavior and whether an empty capture is possible, minor gaps for a read-only capture 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 100%, so both parameters are already documented with defaults and ranges. The description only hints at the duration via 'a few seconds' and says nothing extra about the directory/workspace scoping, so baseline 3 applies.

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 states a specific verb ('collects') and enumerates the resource contents (requests, console.log output, errors) plus the time-bounded scope. It clearly is not get_app_rules or status, though it never names a sibling to contrast with.

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?

It gives actionable operational context: ask the person to open the app or trigger the problem while it runs, and that it only captures a few seconds. It stops short of saying when to prefer another diagnostic tool such as get_app_rules or status.

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