terminal_start

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

With no annotations, the description carries the full burden. It does disclose the destructive side of replace ('Kill an existing session with the same name') and enumerates the return fields including a 'ready reason', which is genuinely useful. It says nothing about session lifetime/persistence, cleanup responsibilities, or failure behavior, which are significant for a long-lived stateful resource.

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?

The purpose is front-loaded in one sentence, then cleanly separated into Args and Returns blocks. Nothing is padded and the parameter list is justified because the schema itself provides no descriptions.

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 an 8-parameter, stateful, no-annotation tool with no output schema, the description covers parameters and return shape well. It stops short of telling the agent how this session relates to the other session tools (send/read/stop) or how long the session lives, which is the main remaining gap.

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, and it does: all eight parameters are explained with concrete values ('powershell', 'pwsh', 'cmd', or an absolute path), defaults (120 cols, 30 rows, server cwd), and semantics (env is merged into the inherited environment, name auto-generates as t1/t2, args are extra shell arguments).

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+resource ('Start an interactive terminal session') and the return payload, so the agent knows exactly what the tool does. It does not, however, contrast itself with the closest sibling, terminal_exec, which an agent could reasonably confuse it with for command execution.

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?

Usage is implied rather than stated: 'interactive terminal session' versus terminal_exec/terminal_send, and the replace flag's kill-and-restart behavior hint at when to use it. There is no explicit when-to-use/when-not-to-use guidance or named alternative anywhere in the text.

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