Skip to main content
Glama
gaztrabisme

deepseek-subagent-mcp

by gaztrabisme

dsh_delegate

Delegate a coding task to a new DeepSeek Harness subagent with its own runtime process, then verify completion using a shell command. Returns an agent ID immediately or waits for results when desired.

Instructions

Start a new DeepSeek Harness subagent on a task.

Returns immediately with an agent_id and run_id unless wait_seconds is set. Each call creates a fresh agent with its own runtime process and session; use dsh_continue to give more work to an agent that already exists.

Args: task: What to do, with a clear definition of done. The child cannot ask you clarifying questions, so state the acceptance criteria. verification: The shell command that proves the task is done, run by this server in the workspace after the child finishes — e.g. "pytest -q" or "npm test && npm run lint". Its exit code decides whether the run is reported completed or completed_unverified. Pass "true" if there is genuinely nothing to check. workspace: Directory the child reads and writes. Relative paths resolve against the server's configured workspace. Defaults to that workspace. instructions: Optional standing guidance prepended to the task, e.g. coding conventions or files to leave alone. model: DeepSeek model id. Defaults to the server's configured model. name: Human label for this agent, shown in dsh_list. wait_seconds: Block up to this long for the run to finish. 0 returns at once.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNo
taskYes
modelNo
workspaceNo
instructionsNo
verificationYes
wait_secondsNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observedv0.2.0

TDQS

A5/5.0
Behavior5/5

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

No annotations are provided, so the description fully discloses behavior: creates a fresh agent per call, returns immediately unless wait_seconds, child cannot ask clarifying questions (must include acceptance criteria), verification exit code decides unverified vs completed, workspace resolution, and defaults. This is thorough behavioral disclosure.

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?

The description is well-structured: a lead paragraph stating purpose and key behavior (fresh process, immediate return), then a clean Args section with one line per parameter. Each sentence adds value; no fluff. Front-loads the most important behavioral facts.

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

Completeness5/5

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

The description covers every parameter with meaning, explains control flow (wait_seconds), explains the verification command's role in determining completion status, and mentions the sibling tool dsh_continue. It is complete enough for an agent to correctly invoke this tool without further context.

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

Parameters5/5

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

Schema has no descriptions (0% coverage). The description compensates fully: it explains task (with acceptance criteria and inability to clarify), verification (shell command, exit code semantics), workspace (relative paths, default), instructions (prepended standing guidance), model (default), name (human label), and wait_seconds (blocking behavior). Every parameter is given meaningful semantics beyond the schema's type-only definition.

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?

The description clearly states the verb (start) and resource (a new DeepSeek Harness subagent), explains the immediate-return behavior, and explicitly distinguishes this from 'dsh_continue' for giving more work to existing agents. This effectively differentiates it from siblings.

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?

The description provides explicit guidance: states when to use dsh_continue for existing agents, explains the wait_seconds behavior, and describes the verification command's role in determining run status. This clearly orients the agent on when to invoke this vs. alternatives.

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

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/gaztrabisme/deepseek-subagent-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server