mcp-ssh

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions execution in sessions or one-time, but lacks critical details: whether this requires authentication, what happens on timeout (timeoutMs parameter), if commands are destructive, error handling, or output format. For a tool that executes commands via SSH (potentially with security implications), this is a significant gap.

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 a single, efficient sentence in Russian that directly states the tool's function. It's front-loaded with the core purpose and includes key contextual details (sessions vs. one-time) without unnecessary elaboration. Every word earns its place, making it appropriately concise.

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 complexity of SSH command execution (4 parameters, no annotations, no output schema), the description is incomplete. It lacks details on authentication requirements, behavioral traits (e.g., is it safe/destructive?), parameter meanings (especially cwd and timeoutMs), and expected outputs. For a tool with potential security and operational impact, this leaves too many gaps for reliable agent use.

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 description coverage is 0%, so the description must compensate for all 4 parameters. It only vaguely implies 'sessionId' (via 'существующей сессии' - existing session) and 'command' (via 'команды' - command), but doesn't explain 'cwd' (current working directory) or 'timeoutMs' at all. The description adds minimal meaning beyond the bare schema, failing to adequately document parameter purposes.

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 action ('Выполнение команды' - executing a command) and the resource ('по SSH' - via SSH), specifying it works in existing sessions or one-time. It distinguishes from siblings like ssh_connect (establish connection) and ssh_disconnect (end connection). However, it doesn't explicitly contrast with ssh_list_sessions (list sessions), which slightly reduces specificity.

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 provides clear context about when to use it: 'в существующей сессии или одноразово' (in an existing session or one-time). This implicitly suggests alternatives: use ssh_connect first for a session, then this tool for commands, or use this tool directly for one-off commands. However, it doesn't explicitly state when NOT to use it or name alternatives like ssh_list_sessions for checking sessions.

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