stop_trace

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

Annotations already flag destructiveHint=true and readOnlyHint=false, but the description goes well beyond them: it specifies what is destroyed (hooks removed, trace detached), what survives (JSONL evidence and summary retained), and two explicit non-effects (no force-stop of the application, no ART deoptimization rollback). This is precisely the added behavioral context annotations cannot convey.

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?

Two sentences, zero filler: the primary action and its effects come first, and the exclusion clause follows. Every clause carries distinct information.

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 destructive, non-idempotent, no-output-schema tool, the description covers side effects, retention, and scope limits well. What is missing is error/edge behavior (e.g., stopping an already-stopped trace, since idempotentHint=false) and any hint of what the response contains beyond retained evidence and summary.

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 description coverage is 50%: analysis_project_id is documented in the schema itself, while trace_id relies on its name, pattern, and length constraints. The description only implies trace_id via "one trace created by this connection" and adds no format or selection guidance, so it does not compensate for the undocumented half. Baseline 3 applies.

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 opens with a specific verb and resource ("Stop and detach one trace") plus a scoping qualifier ("created by this connection"), which immediately separates it from start_trace, get_trace_events, mark_trace, and inspect_trace in the sibling list. It also enumerates the concrete side effects (hooks removed, evidence retained), so an agent knows exactly what this operation is.

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?

It gives clear negative guidance — it will not force-stop an attached application and will not restore explicitly deoptimized ART execution — which tells the agent when this tool is insufficient. It stops short of explicitly naming the alternative tool (e.g., start_trace, inspect_trace) or stating the precondition that a trace must be active, so it is strong but not fully routing.

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