open_on_macOpens a headless session in a Mac terminal window so you can read its output and take over manually; the window then becomes a live session.
Open a headless session in a terminal window on the user's Mac, so the user can read it and take over by hand. The window then becomes a live session.
| Name | Required | Description | Default |
|---|---|---|---|
| session_id | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare this is a non-read-only, non-destructive, non-idempotent, closed-world operation. The description usefully adds that a visible terminal window is created on the user's local Mac and becomes a live session, which is real context beyond the annotations. It omits what happens on a bad/expired session_id, whether repeated calls spawn multiple windows, and what is returned.
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 short sentences, front-loaded with the action and followed by the purpose. Slight redundancy between 'so the user can read it and take over by hand' and 'becomes a live session', but nothing is padded or wasted.
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?
For a one-parameter mutation that has local side effects on the user's machine and no output schema, the description covers the core intent but leaves error behavior, preconditions, and repeat-call behavior unstated. Adequate but with clear gaps for a tool that acts on the user's physical machine.
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 session_id, so the description must carry the semantics. The phrase 'headless session' hints the ID references an existing session, but the description never says the session must already exist, where the ID comes from, or what an invalid ID does.
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?
States a specific verb and resource (open a headless session in a terminal window on the user's Mac) and describes the resulting state (the window becomes a live session). It does not, however, distinguish itself from the sibling start_session, so an agent must infer the boundary between starting a session and surfacing an existing one in a terminal window.
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 rationale 'so the user can read it and take over by hand' implies usage when human interaction/handoff is wanted, and the 'headless session' phrasing hints that a prior session must exist. But there is no explicit when-to-use vs. start_session, no prerequisites, and no statement about what to do if session_id is unknown.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
This server cannot be deployed