shell_open

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

With no annotations, the description carries the full burden of behavioral disclosure. It states persistence but does not disclose that opening a shell creates a stateful resource, starts a process, may need to be closed via shell_close, or how startup_command and env affect the session.

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 a single front-loaded sentence with no redundancy, so it is concise. However, it is so terse that it omits important context about lifecycle and usage; it is under-specified rather than efficiently complete.

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?

An output schema exists, so return-value details are likely covered elsewhere, but that does not compensate for missing lifecycle, parameter, and sibling-relationship context. With zero annotations and 0% schema description coverage, the description is inadequate for an agent to use this tool confidently.

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 should compensate for the undocumented cwd, env, and startup_command parameters. It does not: the parameter meanings are left entirely to inference from their names and schema titles.

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 uses a specific verb ('Open') and resource ('persistent bash command shell'), making the core action clear. The 'persistent' qualifier helps distinguish it from one-off command execution, though it does not explicitly name a sibling alternative.

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?

No guidance is provided on when to use shell_open versus shell_exec or the other sibling tools. It does not mention that a persistent shell should be opened before shell_read/shell_write, or that shell_exec is for non-persistent commands.

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