Skip to main content
Glama
zb-ss

Servonaut

by zb-ss
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

aws_terminate_instance

Permanently terminate an AWS EC2 instance, deleting instance-store data and detaching or destroying EBS volumes. Use in dangerous guard mode after confirming the exact instance ID and region.

Instructions

PERMANENTLY terminate an AWS EC2 instance. Instance-store data lost; EBS volumes detached or destroyed per their DeleteOnTermination flag. Irreversible. Reserved for dangerous guard mode. ALWAYS confirm with the user (state the exact instance ID, region, and any data-loss implications) before calling.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
regionYesAWS region (e.g. us-east-1).
accountNoAccount label the server is in; omit to use the account whose inventory lists it (else the default account).
instance_idYesEC2 instance ID (i-...); '<account>/<id or name>' picks the server of one AWS account.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv2.28.0
    • addedInput schema / properties / account
      Added value: +{
+  "description": "Account label the server is in; omit to use the account whose inventory lists it (else the default account).",
+  "type": "string"
+}
    • changedInput schema / properties / instance_id / description
      Previous value: -"EC2 instance ID (i-...)."New value: +"EC2 instance ID (i-...); '<account>/<id or name>' picks the server of one AWS account."
  2. First observedv1.0.0

TDQS

A4.5/5.0
Behavior5/5

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

With no annotations, the description carries the full behavioral burden and does so admirably: it discloses irreversibility, instance-store data loss, EBS volume detachment/destruction governed by DeleteOnTermination, and a guard-mode restriction. This is exactly the safety context an agent needs before a destructive call.

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?

Front-loads the destructive nature ('PERMANENTLY terminate'), then data-loss mechanics, then the confirmation instruction. Every clause earns its place 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 destructive 3-parameter tool with no annotations and no output schema, the description covers the critical gaps: irreversibility, data-loss consequences, guard-mode gating, and mandatory human confirmation. Nothing essential for correct invocation 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 the schema already documents instance_id, region, and account including the '<account>/<id or name>' syntax. The description only references instance ID and region in the confirmation instruction and adds no new parameter semantics. Baseline 3 is appropriate.

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?

States a specific verb (terminate) and resource (AWS EC2 instance) and immediately disambiguates from the sibling stop/reboot tools with 'PERMANENTLY' and 'Irreversible'. An agent can distinguish this from aws_stop_instance and aws_reboot_instance without opening 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?

Gives clear usage context ('Reserved for dangerous guard mode') and an explicit pre-call requirement to confirm with the user, including what to state (instance ID, region, data-loss implications). It does not explicitly name aws_stop_instance as the non-destructive alternative, but the destructive framing largely implies it.

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

Deploy Server

Other Tools