performance_start_trace

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

No annotations are provided, so the description carries the full behavioral burden and falls well short. It doesn't say whether the trace runs until explicitly stopped, what autoStop does, whether the call blocks, or what artifacts/return values appear. For a stateful performance capture tool in a start/stop/analyze workflow, omitting that this is only the first step is a significant gap.

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 short sentences, front-loaded with the action and then the purpose. No filler, though it is arguably too terse for a 4-parameter tool with weak schema coverage.

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 annotations, no output schema, four parameters (three undocumented), and no explanation of the start/stop/analyze workflow it belongs to, the description leaves too much unspecified for an agent to invoke it confidently in sequence.

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 only 25%: pageId is documented in the schema, but reload, autoStop, and filePath have no descriptions anywhere. The description adds no parameter meaning at all, so it fails to compensate for the low coverage as required.

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 specific verb+resource: 'Start a performance trace on the page.' This is distinguishable from siblings like performance_stop_trace and performance_analyze_insight by the verb alone, so an agent can pick it correctly. It stops short of 5 because it doesn't explicitly scope itself against those siblings.

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 to find frontend performance issues and Core Web Vitals' gives the purpose/motivation for calling it, which is useful usage context. However, it never states when to use this versus the other performance tools, or that a trace typically must be followed by performance_stop_trace and performance_analyze_insight. Usage is implied rather than specified.

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