replay_recording

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

There are no annotations, so the description carries the full burden. It discloses key timing behavior: events are replayed 'honoring their time_ms timeline scaled by speed', which explains the effect of the speed parameter and the relative timing mechanism. It also implies a dependency on a prior recording, but does not state whether it blocks until replay completes or whether it requires the game to be in a specific state; still, the timing disclosure provides useful behavioral context.

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 a single, dense sentence that efficiently packs the core action, target, and the essential timing behavior. Every clause earns its place: 'Replay recorded input events' defines purpose, 'into the running game' specifies context, and 'honoring their time_ms timeline scaled by speed' explains scaling semantics. No filler or redundancy.

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?

Given the tool's moderate complexity (2 params, no output schema, no annotations), the description covers the core replay concept and timing behavior but omits important operational details: whether replay is synchronous, what happens if events are invalid, whether the game must be in play mode, and how to obtain the 'events' array from a recording. The sibling tools (start_recording/stop_recording) suggest a workflow, but the description alone leaves gaps.

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 0%, so the description must compensate. It mentions 'time_ms timeline' and 'scaled by speed', which explains the semantics of the 'speed' parameter, but it does not explain the structure of the 'events' array (e.g., items have input data and time_ms fields). The schema itself provides minimal structure (additionalProperties: {}), leaving a significant gap for the events parameter, though the description's timing detail gives partial value.

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 uses the specific verb 'Replay' and identifies the resource as 'recorded input events' into the 'running game', which clearly distinguishes it from sibling tools like start_recording/stop_recording that capture events. It states the action and the target context, though it doesn't explicitly name a sibling alternative for contrast.

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 implies a context: replaying previously recorded input events into a running game, which is a clear use case. It does not explicitly state when to use this tool versus alternatives (e.g., simulate_sequence for new input sequences), but the sibling tools and the 'recorded' qualifier provide sufficient context for an agent to infer the appropriate scenario.

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