Skip to main content
Glama
Sign In

Spaces by Peakflo

by ai.peakflo
OverviewDiscussionsAdmin

task_complete

Destructive

Complete a human task by submitting an action.

This resumes the workflow execution that is waiting for this task, so an approval can trigger real postings or payments: confirm the action with the user first. The action string describes what action was taken (e.g., "approved", "rejected", "reviewed").

Parameters:

  • taskId: The ID of the task to complete

  • outputs: Object with at least an "action" field. Other fields correspond to the task form fields (e.g., { "action": "approved", "comments": "Looks good" }).

The task must be open (status not_started, triaging, agent_working or ready_for_review).

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>",
      "outputs": "<outputs>"
    },
    "name": "task_complete"
  }
}

Input Schema

NameRequiredDescriptionDefault
taskIdYesThe task ID to complete
outputsYesOutputs to submit. Must include "action" field. Other fields correspond to the task form fields (e.g., { "action": "approved", "comments": "Looks good" }).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already flag readOnlyHint=false, destructiveHint=true and openWorldHint=true, so the safety profile is established. The description adds material context beyond that: completing the task resumes a waiting workflow and can trigger real postings or payments, which justifies the pre-confirmation instruction. It stops short of describing error behavior for a task in an ineligible state or what the call returns.

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

Conciseness4/5

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

The consequence warning is front-loaded immediately after the purpose statement, which is the right priority for a destructive tool. The trailing parameter list largely restates the schema descriptions, so it is mildly redundant but still short enough to earn its space.

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 destructive, open-world mutation with a nested free-form object and no output schema, the definition covers purpose, consequences, preconditions and payload shape. Remaining gaps are the allowed action values (no enum exists) and post-call behavior or response shape, both of which matter given that completing the task cannot be undone.

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 coverage is 100%, so the baseline is 3, but the description adds meaning the schema cannot convey: that extra keys in the free-form outputs object map to the task's form fields, illustrated with a comments example. That explains how additionalProperties=true is meant to be used rather than merely permitting it.

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?

"Complete a human task by submitting an action" names a specific verb (complete) and resource (human task), and the follow-up sentence clarifies the effect (resuming the waiting workflow execution). It is distinguishable from siblings like task_create and task_update in practice, but no sibling is named to draw the boundary explicitly.

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

Usage Guidelines4/5

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

The description states the precondition for use (task must be open with status not_started, triaging, agent_working or ready_for_review) and a required operating procedure (confirm with the user first). It does not name an alternative tool for related cases, such as updating a task without completing it.

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

All Spaces by Peakflo toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources