Skip to main content
Glama

Run a DSH task to completion

dsh_run

Queues a task to the DSH agent and waits for the turn to settle, ideal for short jobs. Blocks until done; for long tasks use the start and wait tools so calls don't time out.

Instructions

Queue a task and wait for the turn to settle. Convenient for short tasks; long tasks should use dsh_start + dsh_wait so the MCP call does not block. Timeout leaves the turn running and returns timedOut:true.

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_run"
  }
}

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.
timeoutMsNoOverall budget in milliseconds; default 15 minutes.
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 exist, so the description carries the burden. It does disclose the key failure mode — a timeout leaves the turn running rather than cancelling, and the response carries timedOut:true — which is genuinely useful behavior that the schema does not state. However it omits whether the queued task persists after timeout, whether a session is created as a side effect, and how to subsequently retrieve that turn's output, leaving real gaps for a mutating 8-parameter tool.

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, front-loaded with the primary behavior, then the alternative, then the edge case. No filler, no restatement of the title, and the most decision-relevant constraint (blocking) appears before the timeout caveat.

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?

There is no output schema, so the description must explain what comes back; it only surfaces the timedOut:true field and says nothing about the success payload, such as final agent text or the session id needed for follow-up dsh_get calls. For a tool whose whole point is returning a settled turn's result, that omission is a meaningful gap against its complexity.

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 description coverage is 100% and every parameter including the fallback chains for cwd/model/provider/connection is documented in the schema itself, so the baseline is met without description help. The description does add meaning for timeoutMs by explaining the consequence of exceeding it (turn keeps running, timedOut:true), which goes beyond the schema's bare "overall budget" text.

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 concrete verb and resource ("Queue a task and wait for the turn to settle") and immediately frames the scope as run-to-settlement, which is distinguishable from dsh_start/dsh_wait. The wording "turn to settle" leans on DSH-internal vocabulary, so an agent unfamiliar with the domain gets slightly less than a fully explicit "runs task to completion."

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

Usage Guidelines5/5

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

Explicitly names the when (short tasks) and the when-not (long tasks), and routes to the concrete alternative pair dsh_start + dsh_wait with the reason (blocking the MCP call). This is exactly the routing guidance needed to pick between the three run-style siblings.

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