Read a text file from one of your servers over SFTP and return its contents. Files over 512 KB or non-text (binary) files are refused — use ssh_exec (e.g. sed/tail) for those.
| Name | Required | Description | Default |
|---|---|---|---|
| host | Yes | Server id from hosts_list | |
| path | Yes | Absolute or home-relative file path | |
| username | No | Login user (defaults to the tunnel's user, else root) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint already signals safety, and the description adds useful behavior: files over 512 KB and binary files are refused, so the agent won't be surprised by failure. This goes beyond what annotations alone communicate.
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, front-loads the core action, and packs the critical limits and alternative into the second sentence without redundancy.
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?
With no output schema, the description explains the return value ('return the contents') and covers the important edge cases. An agent has enough to correctly 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?
Schema coverage is 100%, so all three parameters are already well documented. The description adds no additional param-level detail, which keeps it at the baseline 3.
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 a specific verb and resource: read a text file over SFTP and return its contents. It clearly distinguishes the tool from siblings by noting it is for text files only and explicitly routing large/binary files to ssh_exec.
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 usage boundaries: use this tool for text files under 512 KB, and use ssh_exec for larger or binary files. It also provides concrete examples of how to handle excluded cases with sed/tail.
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.