Create terminal session

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

With annotations providing no read/destructive/idempotent hints, the description carries the burden. It discloses that the session is persistent, that an empty command creates a login shell, and that output can be incrementally read and waited on. It could mention cleanup via terminal_close, but the core lifecycle is transparent.

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 succinct sentences, each earning its place: purpose is front-loaded, empty-command behavior is explained, and follow-up tool usage is directed. No wasted words.

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 covers how to start and interact with the session, and an output schema exists so return values don't need explanation. However, for a stateful resource it omits cleanup guidance (terminal_close) and doesn't describe the cwd/cols/rows semantics, leaving minor usability gaps.

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%, so the description must compensate for undocumented parameters. It only clarifies the 'command' parameter (empty vs non-empty) and says nothing about cwd, cols, or rows, leaving the agent to infer their meaning from names and defaults.

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 opens with a specific verb and resource: 'Start a persistent shell session (or run a command interactively).' It clearly differentiates this from siblings like run_command by emphasizing persistence and cross-call liveness.

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 gives concrete usage context: empty command spawns a login shell kept alive across calls, and it explicitly routes follow-up work to terminal_write, terminal_read, and terminal_wait. It doesn't explicitly contrast with run_command for one-off commands, but the persistence framing makes the intended use clear.

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