Skip to main content
Glama
remote-ssh-mcp
by RuiFG

ssh_set_workspace

Read-only

Connect or reconnect one SSH host and set its remote working directory after validation; omit the path to keep the current directory.

Instructions

Connect or explicitly reconnect one host and set its remote working directory after validation. First connection starts at the login home. Omitting path keeps the current directory. Does not affect other hosts.

Tool call template

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": {
      "hostId": "<hostId>"
    },
    "name": "ssh_set_workspace"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNo
hostIdYesRequired stable host ID returned by ssh_list_hosts. Names are not accepted.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=true), yet the description still adds useful behavior: validation happens before the directory is applied, a first connection starts at the login home, an omitted path leaves the current directory untouched, and effects are scoped to a single host. The one soft spot is that establishing or reconnecting a session is a stateful side effect that readOnlyHint=true does not capture, though it does not contradict it since no data is modified.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, front-loaded with the action, followed by the two default behaviors and the blast radius. Nothing is redundant with the name, and each sentence carries distinct information an agent would otherwise have to guess.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter session tool with annotations and no output schema, the description covers the material points: how connection and directory setting combine, defaults on omission, and per-host isolation. It leaves open what validation failure looks like and whether credentials must already be configured, both of which an agent would want before calling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50%: hostId is documented in-schema as the stable ID from ssh_list_hosts with names rejected, but path has no schema description. The description compensates for exactly that gap by explaining path's default on first connection and on omission, giving the agent enough to decide whether to supply it. It does not say whether path must be absolute or what happens to a relative path, which keeps it below a 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Connect or explicitly reconnect one host and set its remote working directory.' It also bounds scope with 'Does not affect other hosts,' which separates it from host-management siblings like ssh_add_host or ssh_delete_host. It stops short of naming a specific alternative such as ssh_reset_connection, so an agent must still infer which sibling handles connection resets.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied rather than stated: you call it to connect or to change a host's working directory, and 'Omitting path keeps the current directory' tells the agent when the parameter can be skipped. There is no explicit when-not guidance, no prerequisite about credentials (ssh_set_credentials) or host registration (ssh_add_host), and no comparison against ssh_reset_connection or ssh_test_connection.

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