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

Discloses side effects beyond annotations: 'begins wall-clock billing, shows an on-screen API session active indicator, enables observe/input until session.end' and idle auto-end after ~15 minutes. Adds value over destructiveHint and openWorldHint.

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?

Four sentences, front-loaded with main action. Each sentence adds critical information (side effects, cleanup, idle timeout, destination details). No wasted words.

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 billing, idle timeout, and side effects, the description covers prerequisites (USABLE rig), outputs (session_id and Live View URL), and required follow-up (session.end). Well-suited for agent decision-making.

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 has 100% coverage; the description reinforces 'from rigs.list' and 'USABLE rig' but adds no new parameter-specific details beyond what's in the 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 'Start a metered desktop session on a USABLE rig from rigs.list,' specifying the verb (start), resource (desktop session), and scope (from rigs.list). It distinguishes from sibling tools like session.end and session.live_view.

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 explicit guidance: 'Always call session.end when done or abandoning' and 'Do not call if no USABLE rig exists.' Lacks explicit alternatives for read-only cases, but sibling tools cover that context.

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