shell_start

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

Annotations already mark it destructive and non-read-only. The description adds important behavioral context: the session locks the VM and requires explicit unlock via vm_unlock. It also clarifies the 'interactive redirected-pipe' nature, which goes beyond annotations. No contradiction with 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 sentences with no fluff. The first sentence front-loads the primary action and output; the second provides a critical usage warning. Every word earns its place.

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 key aspects: what it starts, the return value, and the locking side-effect with unlock guidance. Given no output schema, it appropriately mentions the session ID. It could be improved by noting available sibling tools for interacting with the session, but this is not essential for the start operation.

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 has 2 parameters with 0% description coverage, and the description does not explain 'command' or 'cwd'. While names hint at meaning (command as the shell command, cwd as working directory), the description adds no additional semantics, leaving ambiguity about how command is used in an interactive session.

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 clearly states the specific action ('Start an interactive redirected-pipe shell session') and the resource (a shell session). It also mentions the return value (session ID), distinguishing it from siblings like shell_exec or shell_write by emphasizing 'interactive' and 'session'.

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 provides clear context by noting the VM lock and instructing to call vm_unlock when finished. However, it does not explicitly compare to alternatives (e.g., shell_exec for non-interactive use) or state when not to use it, so there is no direct exclusion.

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