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

Annotations declare a non-read-only, open-world, idempotent, non-destructive operation, and the description adds genuinely new context: the eligibility gate and the contents of the returned handshake. It does not cover session lifetime, expiry, or whether repeat calls replace an existing session, which matters for an idempotent control channel.

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 short sentences, ordered gate-first, then return payload, then exclusions, then alternatives. No filler and nothing redundant with the schema or annotations.

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?

With no output schema, the description usefully enumerates what comes back (WebSocket URL, commands, schemas, feeds, auth instructions). The main remaining gap is the lifecycle of the session, such as how it is closed or what happens if one is already open, for a tool whose name implies state.

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 100% and the single lease_id is already documented, so the schema carries most of the burden. The description nonetheless adds semantic value by constraining which lease states are acceptable (must be ACTIVE and a remote-control rental), which an agent cannot infer from the schema alone.

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 states a specific action and resource (open a control session) plus the precondition: an ACTIVE configured remote-control rental. It also enumerates the payload (control WebSocket URL, granted commands and schemas, feeds, authentication instructions), which clearly separates it from read-only siblings like get_robot_status or list_robot_commands.

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?

It gives an explicit when ('only for an ACTIVE configured remote-control rental'), an explicit when-not ('personnel-operated and equipment-only service rentals grant no platform controls and cannot open a session'), and a named alternative path for supervisory clients via the MCP command/feed tools.

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