Open Terminal Session

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

Since all annotation hints are false, the description carries the full burden of behavioral disclosure, and it does so thoroughly. It covers persistence, process isolation, name registration, automatic shell fallback with a warning, and the non-idempotent behavior of erroring on duplicate names. This goes well beyond what the annotations themselves reveal.

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 description is well-structured with a core opening sentence, a concise Args block, and then direct usage-oriented guidance. Every sentence contributes either to understanding the tool's behavior or to deciding when to use it. The explicit example of 'server' vs 'git' sessions is illustrative without being verbose.

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 tool has no output schema and sparse annotations, but the description covers the essential runtime behavior, error conditions, default session behavior, and fallback logic. An agent has enough information to call this tool correctly, understand what will happen, and know how to handle common pitfalls. There is no critical missing context.

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?

The input schema already describes all three parameters with 100% coverage, so the baseline is 3. The description adds extra value by explaining shell fallback behavior ('Falls back to powershell automatically (with a warning in the result) if pwsh.exe is not installed') and by framing the name parameter as the key to creating independently named sessions. It does not purely repeat schema content.

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 explicitly states the verb and resource: 'Starts a new, persistent shell process attached to its own pseudo console, and registers it under a name you choose.' It clearly differentiates from siblings by explaining when write_to_terminal auto-creates the 'default' session, and it mentions the distinct use case for named sessions. This is more than adequate for an agent to know exactly what the tool does.

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 explicit when-to-use guidance: 'Use this tool explicitly when you want a second, independently named session... or want to pick the shell/starting directory yourself.' It also states when it is not needed: 'You do not need to call this before write_to_terminal - writing to the "default" session name auto-creates it.' The error condition ('Errors if a session with that name is already open - close it first or pick a different name') further clarifies the usage boundary.

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