restart_terminal

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

No annotations are provided, so the description carries full behavioral burden. It usefully discloses that the conversation is lost, that the operation blocks for up to ~90s, and which attributes are preserved, though it does not discuss permissions or error modes.

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?

Three short sentences, front-loaded with the action, then usage conditions, then effects and timing. No filler; every clause adds useful operational context.

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?

Output schema exists, so return values need not be explained. The description covers the failure conditions, destructive effect, and blocking behavior well, but omits parameter guidance for terminal_id.

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 sole terminal_id parameter. The description refers to 'a terminal's Claude' but never explains terminal_id's format, expected value, or that it identifies the target. Low coverage requires compensation, and none is given.

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 action: replace a terminal's Claude with a fresh instance while preserving id, profile, model, directory, and inbox. The use-case guidance distinguishes it from siblings like interrupt and launch_session.

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?

Explicitly says when to use it: when status is error (Claude exited) or when unresponsive after interrupt. This names the preceding alternative and the failure condition that selects restart.

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