Start System Trace

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

Annotations already flag this as a non-read-only, destructive, idempotent operation, so the safety profile is covered structurally. The description adds valuable platform mechanism context (ETW/strace), but says nothing about the elevated privileges required, the performance overhead of kernel tracing, or what happens if a session with the same name already exists.

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?

A single sentence with zero filler, front-loading the verb and the resource. Nothing to trim.

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?

An output schema exists, so return values need not be explained. But for a destructive, privileged tracing operation the description omits prerequisites (root/admin), overhead warnings, and the lifecycle link to stop_system_trace — meaningful gaps for an agent deciding whether to invoke it.

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% for the single parameter, so the schema already defines session_name. The description adds nothing about naming constraints, whether the name must be unique, or whether reuse is allowed — 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?

States a specific verb ('Start') and resource ('kernel-level event trace'), and even names the underlying mechanisms (ETW on Windows, strace on Linux). It does not explicitly contrast with the sibling stop_system_trace, but the purpose is unmistakable from the first clause.

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?

There is no guidance on when to reach for this versus capture_system_snapshot, query_system_logs, or the paired stop_system_trace, and no mention that a session must later be stopped. The agent must infer the whole workflow.

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