Skip to main content
Glama

desktop_session_start

Create a session directory and manifest to begin a desktop automation session, optionally enabling tracing, cursor overlay, screenshots, or per-subagent cursors.

Instructions

agent-desktop session start: Create a session directory and manifest

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": "desktop_session_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoOptional human-readable session label
cursorNoShow the visual cursor overlay with its default style
no_traceNoCreate the session without automatic tracing
multi_agentNoGive each harness subagent its own cursor; requires --agent-id on desktop actions
screenshotsNoCapture pre/post-action screenshots and refmap copies (requires tracing; sensitive)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the full disclosure burden. It does reveal the concrete side effect (a directory plus manifest is written), which is genuinely useful, but it says nothing about what happens on a duplicate name, where the directory lives, whether sessions must be explicitly ended, or what identifier is returned for later use.

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 short line, front-loaded with the action and its output artifacts; nothing is padded. The only waste is the redundant 'agent-desktop session start:' prefix, which duplicates the tool name.

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?

For a session-creation tool with five configuration flags, no annotations, and no output schema, the description should at minimum say what the caller gets back (session id or path) so subsequent desktop actions can target it. It also omits any note on lifecycle expectations relative to desktop_session_end, leaving a meaningful gap for the agent's first call in a workflow.

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 each of the five optional flags is already explained in the schema, including the non-obvious constraints ('requires tracing', 'requires --agent-id'). The description adds no additional 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?

The description pairs a specific verb ('Create') with a specific resource ('a session directory and manifest'), which is enough to tell it apart from lifecycle siblings like desktop_session_end or desktop_session_list. The leading 'agent-desktop session start:' merely restates the tool name and adds nothing, but the substantive clause is 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?

There is no explicit when-to-use guidance, no mention of prerequisites (e.g. that other desktop_* actions presumably need an active session), and no reference to the end/gc siblings that pair with it. The agent must infer the lifecycle role from the name alone.

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