Skip to main content
Glama

ExducerAI GPU cloud

Stop a deployment

stop_deployment
DestructiveIdempotent

Stop a deployment now: billing ends at this minute and its container and NVMe scratch disk are deleted and cannot be recovered. A request that has not started is withdrawn at no cost. Make sure results are copied off, tell the user the disk is deleted, and get a yes first.

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": {
      "id": "<id>",
      "confirm": "<confirm>"
    },
    "name": "stop_deployment"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesThe deployment id (rnt_… on a live key, snd_… in the sandbox).
confirmYesMust be true. It states that the user approved this exact action after seeing what it does and costs. With a sandbox key (tml_test_…) nothing is real and it may be set freely.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds real substance beyond them: billing stops at the current minute, the container and NVMe scratch disk are permanently deleted, and a queued request costs nothing to withdraw. The explicit instruction to obtain user confirmation before calling also goes past what 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.

Conciseness5/5

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

Two tight sentences with the irreversible consequence front-loaded before the operational checklist. Every clause carries information — cost timing, data loss, no-cost withdrawal, and the confirmation requirement — with no filler.

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 two-parameter destructive tool with full schema coverage, complete annotations, and no output schema, the description covers what is destroyed, what it costs, the no-cost edge case, and the required user-consent step. Nothing an agent needs to decide whether and how to call it is missing.

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 both 'id' (deployment id format) and 'confirm' (must be true after user approval) are already fully documented in the schema. The description's 'get a yes first' restates the confirm parameter's meaning rather than adding format or edge-case detail beyond it, so the baseline 3 applies.

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?

The description opens with a specific verb and resource ('Stop a deployment now') and immediately scopes the effect (billing ends, container and NVMe scratch disk deleted). This is unmistakably distinct from siblings like extend_deployment, get_deployment, or wait_for_deployment without needing to open any schema.

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?

It gives clear preconditions before invoking: copy results off, tell the user the disk is deleted, and get a yes first, plus the useful case that a not-yet-started request is withdrawn at no cost. It stops short of naming an alternative action (e.g. what to use instead if the user only wants to pause or extend), so no explicit when-not routing is provided.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources