Connect to a Device

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

Annotations already mark idempotentHint and openWorldHint, but the description adds crucial context beyond them: it is a no-op if already connected, it opens/focuses a tab with side effects, it will only connect reachable devices, and it never starts an rce emulator. This fully discloses behavioral traits that an agent must know to invoke and interpret the tool correctly.

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?

The description is dense but every sentence carries operational value: purpose, idempotency, exclusions, alternatives, and device-specific preconditions. The most important information is front-loaded, and the structure makes the routing decision and failure conditions easy to follow.

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?

For a single-parameter tool with rich annotations and no output schema, the description covers all invocation-relevant context: what happens on success, when it is unnecessary, idempotency, reachability requirements, and failure behavior. No critical operational gap remains for an agent selecting or calling the tool.

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 description coverage is 100%, and the input schema already defines `device` as a required non-empty string with LAN IP or serial examples. The description mostly restates that, adding only the source provenance ('from list_devices / scan_devices'), which is marginal value over 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 states a precise action: 'Open (or focus, if already open) a Dev Studio device tab for the given Roku' and clarifies the consequence of making it the active target for renderer-routed tools. It explicitly distinguishes the tool from direct-ECP alternatives like keypress and launch_app, so an agent can confidently tell it apart from siblings.

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 explicitly says when the tool is needed (for renderer-routed tools) and when it is not needed ('Not needed for main-direct ECP ops'), and it names test_connection as the alternative for reachability checks. It also gives per-device-type prerequisites (local discoverable, remote RDS Relay online, rce running), leaving no ambiguity about selection.

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