Skip to main content
Glama

Get swarm subagent task result

swarm_result
Read-only

Retrieve the final result text, model information, and token/credit usage for a finished cb_* or sess_* task.

Instructions

Return the final result text, model info, and token/credit usage for a finished cb_* or sess_* task.

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": {
      "taskId": "<taskId>"
    },
    "name": "swarm_result"
  }
}

Input Schema

NameRequiredDescriptionDefault
taskIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already establish readOnlyHint=true and openWorldHint=false, and the description goes beyond them by disclosing the return payload (result text, model info, token/credit usage) — valuable since no output schema exists. The 'finished task' qualifier also hints at a precondition, though it does not say what happens if the task is unfinished or unknown.

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?

A single front-loaded sentence with no filler: the action, the returned data, and the applicability constraint all appear immediately. Nothing is repeated from the name or title.

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 simple one-parameter read whose safety profile is fully covered by annotations and which has no output schema, the description adequately explains what comes back. The only real gap is the unmentioned qd_* prefix and the absence of any pointer to how an unfinished task should be handled.

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?

With one parameter and 0% schema description coverage, the description must carry the burden and does partially: it tells the agent the taskId refers to a cb_* or sess_* task. It omits the qd_* prefix that the schema's regex accepts, leaving the agent unsure whether qd_ IDs are valid here, and it never says where such an ID is obtained (e.g., from swarm_run).

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 ('Return') with a specific resource (the final result of a subagent task) and enumerates the payload: result text, model info, token/credit usage. It is clearly a result-retrieval tool rather than a status or listing tool. It stops short of naming swarm_structured_result, so the distinction from the structured sibling is only implied by the word 'text'.

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?

The qualifier 'for a finished ... task' implies this should only be called after completion, which is useful usage context. However, it never states what to do while a task is still running (e.g., use swarm_status or swarm_wait) nor when to prefer swarm_structured_result over this tool. Guidance is implied rather than explicit.

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