Skip to main content
Glama
kde-desktop-mcp

kde-desktop-mcp

by marvin1099

kde_audio_route_stream

Destructive

Move one live output stream to a chosen sink after checking its exact stream ID and application name. Use it to reroute audio playback for a specific app without affecting other streams.

Instructions

Move one live output stream to a sink after checking its exact stream ID and application name; requires session='user-desktop'.

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": "<session>",
      "stream_id": "<stream_id>",
      "sink_name": "<sink_name>",
      "application_name": "<application_name>"
    },
    "name": "kde_audio_route_stream"
  }
}

Input Schema

NameRequiredDescriptionDefault
sessionYes
sink_nameYes
stream_idYes
process_idNo
application_nameYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true and openWorldHint=true, so the agent knows this is a risky mutation against an external system. The description adds useful context (exact-ID verification, session requirement) but does not say what is destroyed or made unrecoverable if the wrong stream is routed, nor whether the move is reversible.

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 dense sentence that front-loads the action and follows with prerequisites and the session constraint. No wasted clauses, though the semicolon structure packs a lot into one breath.

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?

Assessed at 4 given the missing return-value documentation and the destructive/mutation risk. For a destructive five-parameter tool with no output schema and 0% schema coverage, the description covers the essential verification prerequisite and session gate, but leaves behavior on failure and process_id semantics unaddressed.

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 coverage is 0%, so the description carries the burden. It meaningfully explains why application_name is required (verification/disambiguation, not obvious from the schema) and pins session to 'user-desktop', but process_id is never mentioned and sink_name's relationship to the target is only implied.

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?

The description gives a specific verb ('Move') and a precisely scoped resource ('one live output stream to a sink'), which is clearly distinct from sibling operations like kde_audio_set_default (default sink) or kde_audio_set_volume. It stops short of naming an alternative sibling, but the per-stream routing scope is unambiguous.

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

Usage Guidelines3/5

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

It implies a prerequisite workflow ('after checking its exact stream ID and application name') and states the session constraint, which hints that discovery must happen first. However, it names no concrete alternative tools and gives no explicit when-not guidance or failure conditions.

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