profiler-stream

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

With no annotations, the description fully describes key behaviors: writing a JSONL file, outputting aggregated stats with P95/P99, auto-loading threshold fences, and taking a screenshot on violation. It explains continuous mode returns immediately and samples in background. However, it does not mention how to stop continuous mode or if there are side effects on concurrent profiling.

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 (three sentences) and front-loaded with the main purpose. Each sentence provides essential detail without redundancy, making it easy for an AI agent to parse.

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 description explains the output (JSONL file and aggregated stats) and covers inputs via schema. However, it lacks information on how to stop continuous mode (no stop tool in siblings), and the immediate return value in continuous mode is unclear. This is a notable gap given no output schema.

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?

All five parameters are well-described in the input schema (100% coverage). The description adds minimal extra meaning beyond the schema, primarily reiterating defaults and the continuous mode behavior for 'frames'. Since schema coverage is high, a baseline of 3 is appropriate.

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 specifies the tool's purpose: multi-frame continuous profiler sampling that includes snapshot, GC, hotpath, and call counts. It distinguishes from sibling tools like profiler-snapshot, profiler-gc-alloc, and profiler-hotpath by highlighting the multi-frame/continuous aspect.

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 mentions support for fixed-frame and continuous modes, providing clear context for when to use each. However, it does not explicitly state when not to use this tool or point to alternatives like single-frame profiler tools, leaving some ambiguity for an AI agent.

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