Spaces by Peakflo

task_create

Create a task for work you want to run in the cloud, especially repetitive work. Supply a title and clear instructions in description; optionally supply a cron schedule and IANA timezone (default UTC), an existing agent/user assignee ID, and output fields. Do not guess IDs. Without a schedule or assignee, existing automatic triage selects an eligible agent or human. Recurring tasks reuse their assignee; without one they are assigned to the creator for human action, so to assign a recurring task to the requesting user, omit assignee. Only title, description, schedule, assignee, outputs and clientRequestId are accepted; if the call is refused, the error names the fields to fix. Automatic triage of recurring templates is not supported. Existing cloud scheduling, agent execution, human notifications, permissions, credit checks and review rules apply. Creation queues work; it does not confirm completion. Generate and reuse clientRequestId on retries. Return the task's browser link to the user. Do not request credentials in chat.

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": {
      "title": "<title>",
      "description": "<description>"
    },
    "name": "task_create"
  }
}

Input Schema

Name	Required	Description
`title`	Yes
`outputs`	No
`assignee`	No
`schedule`	No
`description`	Yes
`clientRequestId`	No	Any stable string, generated once per intended task and reused on retries to prevent duplicates.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedNov 5, 2026
- changedInput schema / properties / clientRequestId / description
```
Previous value: -"Generate once per intended task and reuse on retries to prevent duplicates."New value: +"Any stable string, generated once per intended task and reused on retries to prevent duplicates."
```
- removedInput schema / properties / clientRequestId / format
```
Removed value: -"uuid"
```
- addedInput schema / properties / clientRequestId / maxLength
```
Added value: +255
```
- addedInput schema / properties / clientRequestId / minLength
```
Added value: +1
```
First observedNov 5, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true), the description discloses triage fallback behavior, recurring-task assignee inheritance, that creation only queues work rather than confirming completion, that permissions/credit checks/review rules apply, and that errors name offending fields. This is substantially more than the annotations convey.

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 first sentence front-loads the core purpose and every subsequent sentence contributes a distinct rule rather than filler. It is dense and largely unbroken prose, however, so multiple independent rules (triage, recurrence, retries, credentials) blur together and are harder to scan than they could be.

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?

For a mutating, open-world tool with six parameters, nested objects and no output schema, the description covers the return value (the task's browser link), side-effect scope (queued not completed), assignment semantics, and failure behavior. An agent has enough to call this correctly on the first attempt.

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 description coverage is only 17%, so the description carries most of the burden and mostly succeeds: it explains title/description intent, cron plus IANA timezone with a UTC default, assignee as an existing agent/user ID with the behavioral consequence of omission, and clientRequestId generation/reuse. The nested outputs objects (id/name/type/isSecret/optional) are only gestured at as "output fields," leaving their structure unexplained.

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?

Opens with a specific verb+resource: "Create a task for work you want to run in the cloud," and narrows scope with "especially repetitive work," which implicitly separates it from task_list/task_update/task_complete. It never names a sibling explicitly, so it stops short of full differentiation.

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?

Gives explicit when-to guidance (use when work should run in the cloud, particularly recurring work) and concrete exclusions/cautions: "Do not guess IDs," omit assignee to assign a recurring task to the requesting user, and no automatic triage for recurring templates. It also states the retry protocol (reuse clientRequestId) and that the task link should be returned to the user.

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 tools Inspect

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.