shell_start

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

Annotations already indicate destructive=true, readOnly=false, and idempotent=false. The description adds meaningful behavioral context by disclosing that the session locks the VM and that vm_unlock is required afterward, which is beyond what the annotations alone provide. There is no contradiction with the annotations.

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?

Two concise sentences fully capture the action and the key side-effect. The core purpose is front-loaded, and the critical unlock instruction is placed immediately after. No filler is present.

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 the start-session behavior and the lock-related requirement, but it omits how the 'command' parameter should be used and how the returned session ID connects to the session-based sibling tools. Given no output schema, a bit more detail about the expected response and follow-up workflow would make it more complete.

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 only 33%, and the tool description adds essentially no parameter-level meaning. The 'command' and 'cwd' parameters are left undocumented in the schema, and the description does not clarify what command format is expected or what cwd controls. This is a significant gap for an agent trying to invoke the tool correctly.

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 and resource: 'Start an interactive redirected-pipe shell session' and notes that it returns a session ID. This clearly differentiates it from sibling tools like shell_exec, shell_read, and shell_write, even without naming them explicitly.

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 an important lifecycle instruction: the VM remains locked by this session, and vm_unlock must be called when finished. However, it does not explicitly state when to choose this tool over a one-shot shell_exec, nor how it relates to shell_read/shell_write.

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