Stop a persistent Linux machine. The disk and the network address are kept, so starting it again returns the same files at the same address. Stop machines you are done with — a stopped machine costs only its disk.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Machine id |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description goes beyond the annotations (idempotentHint=true, destructiveHint=false) by disclosing that the disk and network address persist, restarting returns the same files at the same address, and a stopped machine costs only its disk. This provides valuable context about state preservation and cost.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences long, front-loaded with the action ('Stop a persistent Linux machine') and provides necessary context without superfluous words. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
This is a simple tool with one parameter and no output schema. The description covers the action, the persistence behavior, usage guidance, and cost implications, making it fully complete for an agent to select and invoke the tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema covers 100% of the parameter (id) with a clear description ('Machine id'). The tool description adds no additional parameter semantics, so the baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool stops a persistent Linux machine, with a specific verb and resource. It distinguishes itself from siblings like scalix_computer_start and scalix_computer_delete by noting that the disk and network address are kept, so this is not a deletion or a 'start' action.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives explicit guidance on when to use the tool: 'Stop machines you are done with' and explains cost implications ('a stopped machine costs only its disk'). It implies that starting again will restore the machine, but does not name the alternative tool or explicitly exclude other scenarios, so it falls just short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Tools are grouped by service prefix and generally target distinct resources/actions. A few execution surfaces could be confused (sandbox_run vs computer_exec vs fn_invoke; build_create vs fn_deploy vs run_deploy), and storage_list is overloaded for both buckets and objects, but descriptions clarify the boundaries well.
The scalix_ prefix plus snake_case is used throughout, and most tools follow <service>_<verb>_<noun>. Minor deviations like scalix_search, scalix_status, and scalix_usage omit a service-domain qualifier, but the overall pattern is predictable and easy to navigate.
53 tools is a very large surface. While the server covers a broad multi-service cloud platform, the count falls well beyond the 25+ threshold and will likely feel overwhelming; many service areas could reasonably be split into separate servers or trimmed.
Several service lifecycles have obvious gaps: the KV store has get/list/set but no delete, storage has upload/download/list but no delete for objects or buckets, functions have deploy/list/invoke but no delete/update, and cron has create but no list/delete. These missing operations create dead ends for agents managing common resources.
