Skip to main content
Glama

Start a DSH task

dsh_start

Queues a task for the DSH coding agent and returns a session ID immediately; omit the ID to start a new session or pass a previous one to continue it.

Instructions

Queue one task for the DSH coding agent and return immediately with a sessionId. Omit sessionId to create a new session; pass a previous sessionId to continue that session. Follow with dsh_wait / dsh_get.

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": {
      "task": "<task>"
    },
    "name": "dsh_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
cwdNoWorking directory for the DSH agent. Defaults to the selected connection cwd, then the MCP server cwd.
taskYesThe task text for the DSH agent.
modelNoModel id; defaults to the selected connection, then DSH settings.
titleNoShort human-readable task title shown in the agent overview.
providerNoDSH provider route; defaults to the selected connection, then DSH settings.
sessionIdNoDSH session id, e.g. session-… returned by a previous call.
connectionNoNamed bridge connection from mcp-bridge.json. Omit to use the configured default.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full burden. It does disclose the most important trait — the call is non-blocking and returns a sessionId immediately — but says nothing about the fact that this launches an autonomous coding agent that can modify the working directory, nor about permission needs, concurrency limits, or failure behavior.

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

Conciseness5/5

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

Three short sentences, action first, then the sessionId branch rule, then the mandatory next step. No filler, and the most decision-relevant information is front-loaded.

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 seven-parameter tool with no output schema, the description covers the essential call-and-follow-up loop an agent needs to drive the async pattern. It stops short of describing what a queued task does on the filesystem and what happens when the sessionId is invalid, which leaves a modest gap.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline would be 3. The description earns above that by explaining the branching semantics of sessionId (omit = new session, reuse = continue), which the schema only hints at with 'returned by a previous call'; the other six parameters are left entirely to the schema.

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 states a specific verb and resource ('Queue one task for the DSH coding agent') and adds the key scope detail that it returns immediately with a sessionId. That async framing implicitly distinguishes it from a blocking sibling such as dsh_run, though it never names that alternative outright.

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?

It gives clear operational guidance: omit sessionId to start fresh, pass a previous sessionId to continue, and follow up with dsh_wait / dsh_get. What is missing is any exclusion rule for when a caller should prefer dsh_run or dsh_sessions instead of queueing here.

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