profile_cpu

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

No annotations provided, so description must cover behavioral traits. It states record and analyze behaviors but doesn't disclose permissions, resource impact, or whether it's safe/idempotent. The description is minimal on non-functional aspects.

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 concise—two sentences plus a returns line—with no fluff. It front-loads the main purpose. Slightly more structure (e.g., bullet points) could improve readability, but it's efficient.

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 full schema coverage and no output schema, the description adequately explains the tool's core function and a key usage pattern. However, it lacks context about when to choose this over sibling performance tools, and doesn't detail the return format.

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 100%, so baseline 3 is appropriate. The description adds only minor clarification for trace_path, which is already well-described in the schema. No additional meaning for other parameters.

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 it records and analyzes CPU performance using Time Profiler, and returns CPU hotspots with severity. It distinguishes from siblings like profile_energy by being CPU-specific, but doesn't explicitly differentiate from profile_raw.

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 a specific usage hint about re-analyzing with trace_path, but lacks explicit guidance on when to use this tool versus siblings like analyze_trace or performance_audit. No when-not-to or alternative guidance.

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