Skip to main content
Glama
Sign In

clousd-mcp

by io.github.Clousd-Android
OverviewDiscussionsAdmin

run_status

Read-only

Follow a run. op=status: status (queued, running, paused = waits for an answer, completed, failed, cancelled), the answer or error, the last steps, per-device results for a run on several phones, and a replay link for the user. op=list: recent runs of this key. op=cancel: stop it. op=message: tell the running agent something (it reads it before its next step).

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": "run_status"
  }
}

Input Schema

NameRequiredDescriptionDefault
opNostatus (default) | list | cancel | messagestatus
runNorun id from run (or runs listed with op=list)
textNomessage: what to tell the running agent
stepsNostatus: how many last steps to show, 0..20
wait_secondsNostatus: wait up to this long for it to finish or ask, 0..50

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

B3.2/5.0
Behavior1/5

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

Annotations declare readOnlyHint=true, yet the description explicitly documents two state-changing operations: 'op=cancel: stop it' terminates a running agent and 'op=message' injects content the agent will act on before its next step. An agent relying on the annotation would treat this as a safe read and could unknowingly abort or steer a live run. The offered detail (statuses, per-device results, replay link, wait semantics) is genuinely useful, but the safety-profile conflict dominates.

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 leading imperative 'Follow a run' front-loads the purpose, followed by a compact op-by-op breakdown with no filler sentences. Minor friction: the nested 'op=status: status (...)' phrasing reads turgidly and the status enumeration is a long parenthetical, but nothing is wasted.

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 five-parameter, zero-required multiplexed tool with an output schema, the description covers the decision space well: all four ops, the status vocabulary including the important 'paused = waits for an answer' state, what status returns, and the wait-for-completion behavior. Return-value detail is a bonus rather than a gap, since an output schema exists.

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 every parameter is already documented in the schema, including op values and the 0..20 / 0..50 ranges for steps and wait_seconds. The description adds only marginal meaning beyond that — it clarifies that `steps` is about the last steps of a status read and that `text` is consumed by the agent before its next step. Baseline 3 is correct when the schema carries the weight.

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 names the resource (a run) and enumerates four distinct operations with their effects: status returns status/answer/steps/per-device results/replay link, list returns recent runs, cancel stops it, message injects text for the running agent. That is far more specific than a name restatement. It stops short of 5 because it never contrasts itself with the closely related siblings `run`, `answer`, and `observe`, so the agent must guess which entry point creates vs. answers vs. inspects a run.

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?

Each op value is given a one-clause purpose, which implies when to pick it (e.g. 'op=list: recent runs of this key' for discovery, 'op=cancel: stop it' to abort). However there are no explicit when-not rules and no routing to alternatives, notably that a run paused 'waiting for an answer' should probably be resolved via the `answer` tool rather than `op=message`; the description leaves that ambiguity in place.

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

All clousd-mcp 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