perf_cpu_profile_start

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

There are no annotations, so the description carries the full burden of behavioral disclosure. It only states the start behavior and the need to call stop later. It does not disclose potential side effects (e.g., performance overhead), statefulness (e.g., what happens if called twice), or what the profiling session produces. This is a significant gap for a tool that initiates a resource-intensive operation.

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 extremely concise, consisting of two short sentences. It front-loads the primary purpose ('Start CPU profiling') and provides a necessary follow-up instruction. Every word earns its place with no unnecessary elaboration.

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 no parameters and no output schema, the description covers the basic start/stop workflow. However, it lacks information about what happens after profiling stops, how results are obtained, or any caveats about the profiling session. It is adequate for a simple start tool but leaves gaps about return values and side effects.

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?

The tool has zero parameters, so the baseline score is 4. The description does not need to explain parameter semantics, and the schema correctly shows an empty properties object. There is no additional parameter detail 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?

The description clearly states the tool's action ('Start CPU profiling') with a specific verb and resource. It also distinguishes itself from its sibling perf_cpu_profile_stop by indicating the start of a paired workflow. However, it does not specify the scope of profiling (e.g., current page or entire browser), so it is clear but not fully exhaustive.

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 explicit usage guidance: perform the actions to profile, then call perf_cpu_profile_stop. This clarifies the intended workflow and pairing with the stop tool. It does not mention alternative tools or when not to use it, but the workflow context is sufficiently clear.

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