performance_start_trace

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

Annotations only say readOnlyHint=false, so the description carries the behavioral burden. It states that a trace will be started, but does not disclose side effects such as page reload behavior, whether an existing file may be overwritten, that the trace runs until stopped, or what the tool returns. With no output schema, the agent is left with meaningful operational uncertainty.

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 succinct sentences with no filler. The action is front-loaded in the first sentence, and the second sentence adds useful application context. Every sentence earns its place.

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 input schema richly documents all parameters and even notes the navigate_page prerequisite for reload/autoStop. However, the tool-level description is incomplete for a state-changing tool with no output schema: it does not mention the trace lifecycle, how results are returned or stored, or that the trace should be stopped or analyzed via sibling tools.

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 the parameter descriptions already explain pageId, reload, autoStop, and filePath. The tool description adds no parameter-level meaning beyond that, so the baseline score 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 opens with a specific verb and resource: 'Start a performance trace on the target webpage.' It also names the intended outcome: finding frontend performance issues, Core Web Vitals, and improving load speed. It is not tautological, though it does not explicitly differentiate itself from sibling tools like lighthouse_audit or performance_analyze_insight.

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 gives clear context for when to use the tool ('Use to find frontend performance issues, Core Web Vitals...'), which helps an agent decide when tracing is appropriate. It does not provide explicit when-not-to-use guidance or name alternatives, but the use case is concrete enough.

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