start_session

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

Discloses side effects beyond annotations: wall-clock billing, on-screen indicator, enabling observe/input, and idle auto-end after ~15 minutes. No contradiction with annotations (destructiveHint, 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 cover all essential information with no redundancy. Critical points are front-loaded.

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?

Covers prerequisites, side effects, idle timeout, required follow-up (end_session), and return values (session_id, Live View URL). No output schema exists, but description provides sufficient guidance.

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 schema covers rig_id with a clear description. The description adds context that the rig must be 'USABLE' and from list_rigs, reinforcing selection criteria beyond 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?

Clearly specifies the action ('Start'), resource ('metered desktop session'), and target ('USABLE rig from list_rigs'). Differentiates from sibling tools like end_session, which ends the 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?

Explicitly states when to call (when a USABLE rig exists) and when not to call, and mandates calling end_session upon completion. Mentions prerequisite list_rigs and side effects that affect usage decisions.

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