run_playcheck

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

With no annotations, the description carries the full burden and does well: it discloses the Edit-mode requirement and restoration on completion/cancellation, that existing game scripts run normally, that it is asynchronous and must be polled by ID, the fields to inspect (development.passed, checks, warnings), and the caveat that frame deltas are this-machine measurements rather than a target-device benchmark. It omits failure/timeout behavior, but the side-effect and state-restoration disclosure is unusually rich.

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?

Front-loads the core capability and then layers prerequisites, lifecycle, and return fields in short sentences with little waste. 'No paid AI is used' is tangential but brief enough not to hurt.

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 no-annotation, no-output-schema, async tool it covers the important operational context (mode requirement, polling, result fields, measurement caveat) and points the agent at where results live. The gap is parameter meaning, which is left entirely to an undocumented schema, so the definition is not fully complete for a 4-parameter call.

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% and there are four parameters (capture, duration, level_id, asset_ids), yet the description explains none of them directly. 'Optional level-clearance checks' faintly hints at level_id but gives no syntax, limits, or meaning for capture/duration/asset_ids, so the description does not compensate for the coverage gap.

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 ('Run') plus the resource ('interaction/range/geometry and optional level-clearance checks') and scopes it to 'real Play/PIE', which distinguishes it from static inspectors like inspect_scene or inspect_performance. It does not name a specific sibling alternative, but the live-playback framing is clear enough to separate it from the other checks/inspection tools.

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 a prerequisite ('Requires Edit mode') and a workflow instruction ('Poll the same ID'), which is more than most. However, it never says when to choose this over siblings such as inspect_performance or review_quality, nor when-not to use it, so selection guidance remains implied.

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