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

The description discloses the most important runtime behavior beyond annotations: the call returns immediately with a run id and queued status, and execution may take from seconds to minutes depending on the target. It also tells the agent where to read results. This goes well beyond the readOnly, idempotent, and destructive hints, with no contradiction.

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?

One sentence that front-loads the action and proceeds through immediate return, duration context, and follow-up route. 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?

For an asynchronous tool with no output schema, the description provides the essential contract: what is returned now (run id, queued status), why the wait may be long, and how to get results. It covers the invocation context and follow-up, making it complete enough for an agent.

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?

The schema already describes scriptId and skipWaitTimes; the description does not elaborate on projectId or add parameter-level constraints beyond the schema. Since coverage is 67% and the remaining parameter name is self-explanatory, the description adds little parameter semantics.

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 starts with the specific verb 'Start playing a saved script,' making the action and resource explicit. It also distinguishes itself from siblings by noting the return behavior and pointing to get_play_status, so an agent can tell it apart from create, validate, delete, and list operations.

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 clearly establishes the context: use this to initiate execution of a script that already exists, then poll for results. It explicitly routes to get_play_status for reading results, but it does not list exclusions or when-not conditions versus other script operations.

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