Sora Commander

Overview Schema Source Related Servers Discussions Admin

list_processes

Lists running process PIDs and executable names in a read-only, bounded scan for safe local inspection. Returns sorted records up to a limit without command lines, credentials, or process control.

Instructions

Read-only bounded PID and executable basename listing using installed psutil or Windows Toolhelp snapshot. No command lines, environment, Owner identity, credentials or process control. Safe error on unavailable/incomplete enumeration; never starts a job or installs dependencies.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "list_processes"
  }
}

Input Schema

Name	Required	Description	Default
`limit`	No	Maximum process PID/name records, 1 to 200; default 100. Total scan capped at 4096 and results sorted by PID.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.2Nov 9, 2026

TDQS

A4/5.0

Behavior4/5

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

With no annotations supplied, the description carries the full burden and largely meets it: it declares read-only behavior, bounded output, the exact enumeration backends, and failure semantics ('safe error on unavailable/incomplete enumeration'). What it does not state is whether results are truncated silently or flagged when the 4096 scan cap is hit, though the output schema likely covers return shape.

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

Conciseness3/5

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

The core operation and its scope lead the description, which is correct front-loading. However, the negative list is dense and partly overlapping ('No command lines, environment, Owner identity, credentials or process control' plus 'never starts a job or installs dependencies' plus 'read-only'), so a few clauses restate the same non-capability and could be consolidated.

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

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single optional parameter, an output schema, and no annotations, the description covers safety profile, enumeration limits, backend fallback and error behavior, which is most of what an agent needs. The only meaningful gap is what happens to results at the scan cap versus the record limit, which is partially handled by the schema.

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% and the limit parameter is fully documented there, including range, default, scan cap and sort order. The description adds only the word 'bounded' and no syntax or default detail beyond the schema, so the baseline of 3 applies.

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

Purpose5/5

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

States a specific verb and resource ('PID and executable basename listing') plus the implementation path (psutil or Windows Toolhelp snapshot) and the bounded/read-only scope. An agent can immediately distinguish this from run_command, read_process_output, or stop_process, all of which operate on an already-known process rather than enumerating them.

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

Usage Guidelines4/5

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

The exclusions do real routing work: no command lines, environment, Owner identity, credentials or process control, and it 'never starts a job or installs dependencies', which steers the agent away from expecting this to launch or inspect anything beyond PID/name. It stops short of an explicit positive instruction such as 'use this to discover a PID before calling read_process_output', so the when-to-use side is inferred rather than stated.

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