This URL transports SSH bytes. End-to-end SSH authentication and host-key verification are still required.
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"id": "<id>"
},
"name": "ssh"
}
}| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, so the safety profile is partially covered. The description does add real context beyond that by stating end-to-end SSH authentication and host-key verification are still required, but it omits what the call actually mutates, whether the URL is ephemeral or persistent, and who must perform the verification.
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?
It is short and free of padding, but the brevity comes from under-specification rather than precision. The opening sentence uses a dangling referent ('This URL') that no parameter or return value establishes, so the front-loaded material is confusing rather than informative.
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, no annotation explaining side effects, and zero parameter documentation, the description should carry the full burden of explaining what invoking the tool produces and how the returned endpoint is used. It does not, leaving the agent unable to predict the result of a non-read-only call.
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% for the single required 'id' parameter, and the description does not compensate at all: it never says whether 'id' is a machine ID, key ID, or session ID, nor what format it takes. The agent is left to guess the identifier's meaning.
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 never states the action the tool performs or what 'id' identifies; it asserts 'This URL transports SSH bytes', referring to a URL that is not a parameter and does not say whether the tool mints a tunnel URL, opens a session, or proxies bytes. An agent cannot tell from this text what calling 'ssh' actually does, nor how it differs from siblings such as exec or machine_request.
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?
There is no when-to-use or when-not-to-use guidance, and no alternatives are named even though exec, machine_request, and machine_health exist nearby. The only constraint given is a prerequisite (SSH auth and host-key verification), which is not the same as routing 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.