Run a single shell command on one of your servers and return its combined output. Runs keyless over Termalin's tunnel — no SSH key, and the server needs no open inbound port.
| Name | Required | Description | Default |
|---|---|---|---|
| host | Yes | Server id from hosts_list | |
| command | Yes | Shell command to execute | |
| username | No | Login user (defaults to the tunnel's user, else root) | |
| timeoutSeconds | No | Max seconds to wait (default 60, up to 300) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description reveals behavioral traits beyond the annotations: it returns combined output, requires no SSH key, and needs no open inbound port. These statements complement the destructiveHint and readOnlyHint annotations, adding context about how the command is transported and what output to expect.
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?
Two compact sentences with no filler. The first sentence front-loads the verb, target, and output; the second adds critical transport context. Every phrase contributes to understanding the tool.
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?
Given the full input schema, the destructive/read-only annotations, and the absence of an output schema, the description provides enough to invoke the tool correctly: what the command does, how output is returned, and the connection model. It does not mention exit-code behavior or timeout semantics, but those are minor gaps.
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 schema already provides descriptions for all four properties (host, command, username, timeoutSeconds), so schema coverage is 100%. The tool description does not add new meaning about the parameters themselves; it only repeats the operation context. Thus baseline 3 is adequate.
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 states the specific verb and resource: 'Run a single shell command on one of your servers and return its combined output.' This clearly distinguishes the tool from siblings like sftp_read/write, which perform file operations rather than command execution. The transport detail further disambiguates the tool.
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 clear context: this is for one-off shell commands on a server, executed keylessly over Termalin's tunnel with no SSH key or open inbound port. It does not explicitly mention sibling tools or say when not to use it, but the command-execution framing provides enough situational guidance.
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.
Every tool maps to a distinct action: password generation, host enumeration, SFTP file listing/reading/writing, and SSH command execution. Although sftp_read and ssh_exec could both be used to retrieve file contents, the descriptions explicitly separate them by file type and size.
Most tools follow a consistent <resource>_<verb> pattern: hosts_list, sftp_list, sftp_read, sftp_write, and ssh_exec. generate_password is the only outlier using <verb>_<noun>, but it is still clear, short, and doesn't cause real confusion.
Six tools is a tight, well-scoped set for managing remote servers via Termalin. Each tool covers a practical need without redundancy or feature bloat.
The main server-management workflow is covered: list hosts, execute commands, list files, read files, write files, and generate passwords. Minor gaps exist around SFTP operations like delete, move, rename, or create-directory, but these can be worked around with ssh_exec.