clousd-mcp

schedules

Destructive

Tasks that run by themselves. op=list: id, name, task, phones, at, days, tz, enabled and the runs it started last time. op=add: run task on devices at at on days, or every hour (every=hour), or only on demand (trigger=api); each firing starts runs like the run tool. op=run: start it now. op=toggle: pause or resume. op=delete: remove it.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "schedules"
  }
}

Input Schema

Name	Required	Description	Default
`at`	No	add: time HH:MM (every=hour: only the minutes count)
`op`	No	list (default) \| add \| run \| toggle \| delete	list
`tz`	No	add: IANA time zone of `at`, e.g. Europe/Berlin (ask the user; default UTC)	UTC
`days`	No	add: days 1-7 (1 = Monday), comma-separated; empty = every day
`name`	No	add: a short name
`task`	No	add: the task in plain words, like for run
`every`	No	add: day (default) \| hour	day
`devices`	No	add: devices, comma-separated or a JSON list
`trigger`	No	add: empty = by time \| api = only when started with op=run
`schedule`	No	run / toggle / delete: schedule id from op=list
`credentials`	No	add: saved logins "package/name", comma-separated

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 5, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already flag destructiveHint=true and openWorldHint=true, and the description is consistent with them ("op=delete: remove it"). Beyond the annotations it adds real behavioural context: that each firing spawns runs like the run tool, that toggle means pause/resume rather than delete, and that trigger=api makes a schedule manual-only. It does not say whether delete also wipes past run history or what permissions adding a schedule requires.

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?

Front-loaded purpose followed by a compact op-by-op breakdown, with no filler sentences. The telegraphic style is efficient for an 11-parameter multiplexed tool, though the semicolon-chained add clause takes a careful read.

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 an 11-parameter multiplexed tool with an output schema, the description covers what each op needs and returns for list. Minor gaps: the list field enumeration mentions "phones" while the schema calls the parameter `devices`, and `credentials` is never mentioned in the description despite being an add-mode input.

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?

Schema description coverage is 100%, so the schema already documents all 11 parameters, and the description mostly mirrors that per-op grouping. The one genuine addition is the relational synthesis in op=add — coupling `task`, `devices`, `at`, `days`, and the every=hour / trigger=api alternatives — which tells the agent how the fields combine. Baseline 3 is appropriate given the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a plain-language purpose ("Tasks that run by themselves") and then defines each of the five operations with a specific verb+object: list, add, run, toggle, delete. It also distinguishes itself from the sibling `run` tool by noting that "each firing starts runs like the run tool", so an agent can tell recurring schedules apart from one-off execution.

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?

Guidance is given for each operation ("op=run: start it now", "op=toggle: pause or resume", "op=delete: remove it") and the add-mode options are enumerated with the selector in parentheses (every=hour, trigger=api). It stops short of explicit guidance on when to prefer a schedule over the sibling `run` tool, or of stating prerequisites such as needing credentials saved first.

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

All clousd-mcp 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.