stop_profiler

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

With only readOnlyHint=false/destructiveHint=false in annotations, the description carries real behavioral weight: it clarifies that stopping may just read back an expired capture, that results can be re-fetched with a different sort, that times are elapsed not CPU, that inclusive rows overlap and must not be summed, and that it errors when nothing was started.

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?

Dense and front-loaded: the action leads, then the read-back caveats, then the return payload list. Every clause carries information, though the enumerated return fields are somewhat long for a tool that has an output schema.

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?

Covers the no-capture error case, the elapsed-vs-CPU timing caveat, the non-summing warning for inclusive rows, and the return shape, so an agent can invoke and interpret results correctly without additional sources.

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 the baseline is 3, but the description adds meaning beyond the schema by tying 'sort' to re-reading the same capture and by contrasting selfMs (own time) vs totalMs (inclusive) vs calls, which is directly the semantic distinction the sort enum encodes.

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 ('Stop the capture started by start_profiler and rank the recorded functions') and names the sibling that creates the capture, so the agent can distinguish it from start_profiler/profile_project immediately.

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?

Explains the read-back semantics: a capture that hit its time limit is read as-is and can be re-read with a different sort, plus the failure condition (errors if no capture was started). It stops short of an explicit when-not/alternative routing, but the context is clear.

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