Skip to main content
Glama
meshive-mcp

meshive-mcp

Official
by meshive

Start Pod

start_pod
Idempotent

Preview and then start a stopped pod, resuming hourly billing. First call shows current state and price without changes; confirm to start with a chosen placement or server pick.

Instructions

Start a stopped pod; hourly billing resumes. With confirm=false (default) it only returns the pod's current state and hourly price and changes nothing; call again with confirm=true after the user agreed to pay again. pod is the pod_name from the pods tool; a display name works on the preview, and confirm=true needs the returned pod_name. placement: omit it (default) and the server picks what the console's Start button would; the result's placement says which one it used. Or choose: "same_node" starts it on its original machine now; "wait_same_node" waits until that machine has room and then starts it there; "any_node" moves it to another machine now; "wait_any_node" waits until any machine has room and starts it there. A waiting pod shows as waiting in the pods tool. any_node and wait_any_node can move the pod: any scratch disk it has is then permanently deleted and attached local storage stays on the old machine. For those two, set allow_data_loss=true only after separate explicit consent to that permanent loss for this pod and placement. allow_data_loss is only sent with an explicit placement: when the server's own pick would move a pod with a scratch disk, the call fails with data_loss_consent_required and names that placement. Asynchronous — poll pods for running. Every write requires operation_id. Reuse the ID returned by the preview, or generate a UUID before the first call. Keep it for confirmation and all retries; a new ID means a new operation. After a timeout, check operation_status and resource state before retrying.

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": {
      "pod": "<pod>"
    },
    "name": "start_pod"
  }
}

Input Schema

NameRequiredDescriptionDefault
podYes
confirmNo
placementNo
workspaceNo
operation_idNo
allow_data_lossNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.9/5.0
Behavior5/5

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

Goes well beyond the annotations: discloses that billing resumes, that the call is asynchronous (poll pods for `running`), that any_node/wait_any_node can permanently delete a scratch disk, and that a server-chosen placement may fail with data_loss_consent_required. The operation_id idempotency contract (reuse for confirm and retries, new ID = new operation) is exactly the kind of stateful behavior annotations cannot express. There is mild tension with destructiveHint=false, but the destructive path is gated behind an explicit opt-in flag plus separate user consent, so it is disclosure rather than contradiction.

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 with purpose and the preview/confirm rule, then layered by parameter. It is long and per-parameter rather than prose, and the placement section partly restates itself ('any_node and wait_any_node can move the pod'). The density justifies its length, but a little tightening is possible.

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 6-parameter mutation with an output schema, the description covers the state machine, consent gating, async polling, retry/idempotency guidance, and error name. Nothing an agent needs in order to call this safely and correctly is missing, and return values are correctly left to the output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry the load and it does: `pod` provenance (pod_name from pods; display name works on the preview but confirm=true needs the returned name), all four `placement` values with their wait-vs-immediate and move semantics, `confirm` default behavior, `allow_data_loss` conditions and why it only applies with an explicit placement, and `operation_id` lifecycle. Only `workspace` is left unexplained, a minor gap against an otherwise exhaustive treatment.

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 precise verb+resource+precondition: 'Start a stopped pod; hourly billing resumes.' The 'stopped' qualifier implicitly separates it from restart_pod, and the description names sibling tools (pods, operation_status) where their behavior matters. An agent can identify the operation without opening the schema.

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?

Explicitly defines the two-step flow: confirm=false is a no-op preview, then confirm=true only after user agreement to resume billing. It also routes the agent to `pods` for polling and operation_status for timeouts, and states the consent precondition for allow_data_loss. When-to-use and when-not-to-proceed are both covered.

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