Systems Manager

Start System Trace

start_system_trace

DestructiveIdempotent

Starts a kernel-level event trace using ETW on Windows or strace on Linux, letting you capture system activity for a named session.

Instructions

Start a kernel-level event trace (ETW on Windows, or strace on Linux).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "session_name": "<session_name>"
    },
    "name": "start_system_trace"
  }
}

Input Schema

Name	Required	Description	Default
`confirm`	No	Explicit confirmation. Pass true when the client cannot answer an approval prompt.
`session_name`	Yes	Name of the trace session

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv2.2.9Nov 3, 2026

addedInput schema / properties / confirm

Added value: +{
+  "default": false,
+  "description": "Explicit confirmation. Pass true when the client cannot answer an approval prompt.",
+  "type": "boolean"
+}

First observedv2.2.5Oct 24, 2026

TDQS

C2.9/5.0

Behavior2/5

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

Annotations already declare destructiveHint=true, idempotentHint=true, readOnlyHint=false, so the safety profile is covered structurally. However, the description does nothing to explain why starting a trace is flagged destructive — no mention of performance overhead, elevated-privilege requirements, trace-session lifecycle, or what gets left behind if never stopped. It only adds platform mechanism detail, which is minor.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, front-loaded sentence with no filler or redundancy. It is efficient, though the brevity comes at the cost of the operational context an agent would need.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

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 no explanation. But for a destructive, privileged, session-oriented operation, the description omits the essential context: that it pairs with stop_system_trace, that elevated permissions are required, and that the trace must be cleaned up.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, including the non-obvious 'confirm' flag documented as needed when the client cannot answer an approval prompt. The description adds no meaning beyond that, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Start a kernel-level event trace') and names the underlying mechanisms (ETW, strace), so the agent knows exactly what capability is being invoked. It does not explicitly differentiate from the obvious sibling stop_system_trace, but the verb 'Start' makes the pairing clear.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this versus the many other diagnostic siblings (capture_system_snapshot, query_system_logs, get_process_details) or versus sm_system_operations. No mention that a trace session must later be closed with stop_system_trace, and no prerequisite information such as required root/administrator privileges.

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