Run shell commands in a persistent local terminal session that supports later stdin and paginated output, while enforcing a configured blocklist for safety.
Start a shell command in a persistent local terminal session. The session can later receive stdin and expose paginated output. Commands are checked against the configured blocklist.
| Name | Required | Description | Default |
|---|---|---|---|
| wait_ms | No | ||
| shell_path | No | ||
| command_line | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate destructiveHint=true and readOnlyHint=false, so the mutation risk is covered. The description adds useful context beyond annotations: commands are checked against a blocklist, sessions are persistent, output is paginated, and stdin can be provided later.
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 tight sentences with the action front-loaded. The first sentence states the verb and resource; the second adds lifecycle and safety context. No filler or 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?
The description sketches the full workflow—start, later stdin, paginated output, blocklist—but omits practical integration details such as how the session is identified after creation, how output is retrieved via lb_shell_output, and how to terminate the session. Since there is no output schema, these missing return-value and follow-up details leave an agent partially guessing.
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%, and the description does not compensate. It only implies command_line's role via 'shell command', while wait_ms and shell_path are left entirely unexplained. The parameter names are somewhat self-evident, but no real semantic guidance is provided.
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 precise action and resource: start a shell command in a persistent local terminal session. It also distinguishes this tool from siblings like lb_shell_output, lb_shell_input, and lb_shell_kill by emphasizing session creation and later stdin/output capabilities.
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 implies when to use the tool: when a command should run in a persistent session that can later receive stdin and expose paginated output. However, it does not explicitly name alternatives or state when not to use it, leaving usage guidance mostly inferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.