ssh_shell_open

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

With no annotations, disclosure is thorough: describes idempotency (no-op if open), return value (confirmation), and that it preserves state. Could mention potential side effects but overall strong.

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?

Extremely concise with no unnecessary words. Well-structured: purpose first, then idempotency note, then clear Args/Returns sections.

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?

Given tool complexity, covers essential aspects: purpose, idempotency, parameter details, return value. With output schema available, description sufficiently 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 coverage is 0%, but description compensates by describing all parameters: session_id as return from ssh_connect, and defaults for term, width, height. Adds meaning beyond schema.

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 it opens a persistent interactive shell that preserves state across calls, and explicitly distinguishes from siblings like ssh_execute by noting it's ideal for screen/tmux and long builds.

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?

Provides context for when to use (persistent shells, long builds) and notes no-op behavior. However, lacks explicit guidance on when not to use or alternatives like ssh_execute for one-off commands.

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