Skip to main content
Glama

dsh_team

Coordinate native DeepSeek Harness agent teams by opening sessions, dispatching tasks, reviewing worker outcomes, and completing work with evidence.

Instructions

Official Native Team control: open/snapshot, Worker/task operations, review, explicit final complete(evidence), archive/restore, capabilities and help. view=summary|models applies ONLY to capabilities, never snapshot/help. snapshot includes workerRoutes. complete requires accepted current revisions, quiescence and acknowledged events; starts the persisted 90-day auto-archive clock. Permanent deletion unsupported/off. Mutations need stable requestId. Follow next_action; Worker count never proves planned dispatch is complete.

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": {
      "action": "<action>"
    },
    "name": "dsh_team"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNo
viewNo
modelNo
ownerNo
actionYes
promptNo
targetNo
taskIdNo
teamIdNo
outcomeNo
subjectNo
evidenceNo
providerNo
blockedByNo
requestIdNo
workspaceNo
permissionNoNew Teams default to read-only; choose workspace-write for implementation at first open/delegate. Existing Team grants are immutable.
questionIdNo
taskActionNo
descriptionNo
writeScopesNo
questionActionNo
reasoningEffortNo
expectedRevisionNo

Output Schema

NameRequiredDescriptionDefault
okYes
dataNo
errorNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.8.0-rc.8

TDQS

B3.2/5.0
Behavior4/5

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

The description adds real behavioral context beyond the annotations: mutations require a stable requestId, complete requires accepted current revisions plus quiescence and acknowledged events, completion starts a persisted 90-day auto-archive clock, and permanent deletion is unsupported/off. These are exactly the kind of side effects and preconditions an agent needs. Gaps remain on other mutating actions (archive/restore semantics, interrupt/stop effects), which keeps it from a 5.

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

Conciseness3/5

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

The action inventory is front-loaded, and most sentences carry information (constraints, preconditions, next_action). But the text is densely packed into run-on sentences with several constraints compressed into one line, making it harder to scan than a structured per-action breakdown would be.

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?

An output schema exists, so return values need not be explained. But for a 20-action dispatcher with 24 parameters, the description never maps parameters to actions or states per-action preconditions beyond complete(), leaving the agent to guess which fields each action requires. Relative to the tool's complexity, this is significantly under-specified.

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

Parameters2/5

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

Schema description coverage is 4% across 24 parameters, so the schema carries almost no meaning and the description must compensate. It clarifies only `view` scoping, `requestId` stability, and `evidence` as a complete() requirement. Nothing is said about taskId/teamId patterns, expectedRevision, taskAction, questionAction, blockedBy, writeScopes, or which parameters apply to which action.

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 names the resource (Native Team) and enumerates the action families it covers: open/snapshot, Worker/task operations, review, complete(evidence), archive/restore, capabilities and help. That maps closely onto the action enum, so an agent can tell what the tool does. It does not differentiate itself from the siblings dsh_team_wait or dsh_delegate_task, which keeps it from a 5.

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?

Some usage rules are explicit: 'view=summary|models applies ONLY to capabilities, never snapshot/help' and the preconditions for complete. 'Follow next_action' gives a control-flow instruction. However, there is no guidance on when to pick this tool over the sibling wait/delegate tools, and no per-action selection guidance across the 20 actions, so usage is only partially implied.

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

Deploy Server

Other Tools