performance_start_trace

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

With readOnlyHint=false already indicating the operation is not read-only, the description adds minimal behavioral context. It does not warn about side effects like the automatic reload (which is covered in the schema but not the description). It mentions what insights can be gained, but not what the trace does to the page or runtime. Given annotations carry the safety profile, this is adequate but not rich.

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 two short sentences, front-loaded with the verb and resource. The second sentence explains the purpose without waffling. Every word adds value, and it is succinct.

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?

The tool is a start-trace action with well-documented parameters and no output schema. The description covers the core trigger and use case. It does not explicitly mention the full workflow (start → stop → analyze), but sibling tools imply this, and the schema's reload guidance covers setup. This is nearly complete for selection and invocation, though it could mention stopping the trace.

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% and each parameter has a detailed description, including usage guidance for `reload` and `filePath`. The description itself does not explain parameters, but the schema fulfills that burden. Therefore, a baseline score of 3 is appropriate since the tool description adds no param-specific info beyond what the schema provides.

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 action ('Start a performance trace') and the target resource ('the selected webpage'), and it differentiates from sibling tools like performance_stop_trace and performance_analyze_insight by focusing on initiation. The added use case (Core Web Vitals, page load speed) reinforces its purpose.

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 provides clear context on when to use the tool: 'Use to find frontend performance issues, Core Web Vitals...' It does not explicitly mention when not to use it or name alternative tools, but the purpose is specific enough to guide selection. It could improve by referencing complementary tools like performance_stop_trace.

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