TaskOutput tool description
SDK-CLI Agent SDK, print mode, v2.1.248. The text the model is given for this tool, line by line, with each line marked against the previous capture taken the same way. One model string produces this prompt.
As described in the system reminder: claude md request, not the ordinary one.
This tool has no description in the capture before this one on this arm, so the left gutter is empty rather than marking every line as new.
Lines121,049 characters
Moved—nothing to compare against
Sent to1model strings get this description
Copies1distinct descriptions under this name
Parameters33 of them required
Every tool→every description on this arm
Plain text · sha256 e8ce9d8a6c75
The description, line by line
12 lines One line number, because there is no previous capture to number against.
1
DEPRECATED: Background tasks return their output file path in the tool result, and you receive a <task-notification> with the same path when the task completes.
2
- For bash tasks: prefer using the Read tool on that output file path — it contains stdout/stderr.
3
- For local_agent tasks: use the Agent tool result directly. Do NOT Read the .output file — it is a symlink to the full subagent conversation transcript (JSONL) and will overflow your context window.
4
- For remote_agent tasks: prefer using the Read tool on the output file path — it contains the streamed remote session output (same as bash).
5
6
- Retrieves output from a running or completed task (background shell, agent, or remote session)
7
- Takes a task_id parameter identifying the task
8
- Returns the task output along with status information
9
- Use block=true (default) to wait for task completion
10
- Use block=false for non-blocking check of current status
11
- Task IDs can be found using the /tasks command
12
- Works with all task types: background shells, async agents, and remote sessions
What it accepts
3 parameters The JSON parameter schema sent beside this description, 532 characters of it. Name, type, then whether the client marked it required.block
boolean
required
Whether to wait for completion
task_id
string
required
The task ID to get output from
timeout
number
required
Max wait time in ms
sha256 fd31873a9493 · the schema as the client sent it:
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false,
"properties": {
"block": {
"default": true,
"description": "Whether to wait for completion",
"type": "boolean"
},
"task_id": {
"description": "The task ID to get output from",
"type": "string"
},
"timeout": {
"default": 30000,
"description": "Max wait time in ms",
"maximum": 600000,
"minimum": 0,
"type": "number"
}
},
"required": [
"task_id",
"block",
"timeout"
],
"type": "object"
}