performance_trace_start

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

With no annotations, the description carries full burden. It discloses that the tool starts a trace on the active tab and that only one trace can be active. However, it does not mention prerequisites (e.g., whether DevTools must be attached), potential errors if already running, performance overhead, or side effects. This leaves gaps for safe and correct invocation.

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 efficient: a short intro, a usage note, and a clear args list. The default categories string is lengthy but necessary. No wasted sentences.

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?

Given that an output schema exists (not shown), the description correctly omits return values. It covers the tool's action, usage pattern (start/stop), and parameters. Minor gaps: no prerequisites or error handling details, but it is mostly complete for this tool's complexity.

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 0%, so the description must compensate. It explains the categories parameter with a default value and lists the trace categories, and describes the screenshots parameter as a boolean for including frames. This adds meaningful context beyond the schema's type and default, though it could clarify that categories is a comma-separated string.

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 clear verb+resource: 'Start Chrome DevTools performance trace on the active tab.' It distinguishes itself from sibling tools like performance_trace_stop (paired stop function) and performance_metrics (likely a different tool for metrics). The purpose is unambiguous.

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 explicitly states to use stop() to save the trace and notes that only one trace can be active at a time, providing clear usage context. However, it does not explicitly guide when to use this tool versus alternatives like performance_metrics or performance_timeline, though the start/stop pairing implies it for detailed traces.

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