Freeze or resume the running game

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

Annotations only declare idempotentHint, so the description carries the burden and does so richly: it discloses exactly what halts (SceneManager.updateMain, event interpreter, input sampling), what persists (last frame, screenshot/eval/diagnostics), and the non-obvious side effect that live_key input is dropped while paused.

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 behavioral consequence is front-loaded in the first sentence and every subsequent clause adds distinct, load-bearing information. No filler or redundancy despite its length.

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 mutation tool with no output schema and minimal annotations, the description fully covers the state change, its scope, its side effects, and the resume path. An agent has everything needed to call it correctly.

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 0% with a single boolean, so the description must compensate, and it does: 'Resume with paused: false' pins down the polarity of the parameter. It could add a touch more (e.g. default state), but the core semantics are covered.

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: stop/resume the engine's update loop. It explicitly contrasts with the surrounding live_* family by naming what still works (live_screenshot, live_eval, live_diagnostics) and what is dropped (live_key), so an agent can place it precisely among 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?

Gives clear context for when the effect applies (update loop skipped, input unsampled) and how to reverse it (paused: false). It stops short of explicitly routing to alternatives like live_step for frame advancement, so it is clear context without full when-not/alternative guidance.

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