launch_start

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

Annotations cover only the safety profile (readOnly=false, openWorld=true, idempotent=false). The description adds substantial behavior beyond that: it opens a browser window, popups can be blocked, the editor auto-bridges, adopted=true only occurs when no options are passed, and sessionId changes per launch. This is the kind of context the structured fields cannot carry.

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?

Purpose and prerequisite status are front-loaded, and the return-field explanation is dense but earns its space. It runs long with several clauses, but almost nothing is filler; a slight trim of the return-value enumeration would tighten it.

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 carries the return contract well ({url, sceneId, ready, adopted, engineVersion, device, deviceType, sessionId}) plus failure modes and adoption semantics. The main remaining gap is the undocumented boolean launch flags, which an agent might need to pass.

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 only 38% across 8 params. The description does add meaning for device (requested override), engineVersion, and the 'no options passed' adoption rule, but debug, bundles, profiler, miniStats, concatenate and waitMs are left undocumented in both schema and description. Baseline 3 given the partial compensation.

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?

States a specific verb+resource ('Start a real Launch runtime instance of the current scene') and anchors it to the concrete editor affordance ('the editor's Launch button'). It also declares its systemic role ('the prerequisite for all runtime tools'), which no sibling shares, so the agent can distinguish it immediately.

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 names when NOT to use it ('to screenshot the editor use capture_viewport; to change the scene use edit-time tools') and routes siblings (capture_runtime, read_runtime_logs) as downstream consumers. It also gives a recovery path when ready=false (poll read_runtime_logs or retry) and explains how to force a fresh launch.

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