How To Collect a CPU Profile

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

With no annotations, the description carries the full behavioral burden. It clearly discloses that the tool returns instructions rather than performing profiling itself, and it notes the relationship to load_profile. It does not detail output structure, but that is less critical for a how-to recipe tool.

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?

Three compact sentences fully convey purpose, trigger condition, and usage direction. Key information is front-loaded and there is no filler.

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?

For a simple tool with one optional enum parameter and no output schema, the description is complete: it says what is returned, when to call it, and how to choose the parameter. The sibling tool reference helps the agent understand the overall workflow.

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 schema already provides 100% coverage for the single 'scenario' parameter, including enum descriptions. The description reinforces selecting the scenario that matches execution, but does not meaningfully add beyond the schema.

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 returns a ready-to-run command and step-by-step recipe for capturing a V8 CPU profile and loading it with load_profile. It identifies the resource and action precisely, and the 'when you do not yet have a .cpuprofile file' condition distinguishes it from analysis tools.

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 says to use this tool when no .cpuprofile file exists, and tells the agent to choose the scenario matching how the code runs. It also references load_profile as the follow-up tool, though it does not explicitly enumerate all sibling exclusions.

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