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

The description explains the waiting behavior, terminal states, and timeout handling in detail. The annotations (readOnly, idempotent) are consistent with the described non-mutating, repeatable operation, and there is 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?

The description is a single concise paragraph that efficiently communicates the core function, the expected outcome, and the retry instruction. It avoids redundancy and focuses on essential information.

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?

The tool definition is complete for its purpose. It covers the wait semantics, terminal states, timeout behavior, and the retry condition. Given the schema and the simple nature of the operation, no additional context is necessary.

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 provides explicit descriptions: run_id is identified as a run ID string with a format hint, and timeout_seconds specifies its purpose, default, maximum, and the behavior on expiry. These descriptions fully detail the parameters without ambiguity.

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 clearly states the tool waits for a run to settle into a terminal state (completed, failed, or needs_input) and returns that state. It distinguishes itself from sibling tools like get_run (which returns current state) and cancel_run (which cancels) by focusing on the blocking wait behavior.

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?

It specifies that on timeout, it returns 'wait_timed_out' and advises the agent to call again, effectively guiding the retry pattern. While it does not explicitly contrast with alternatives like get_run, the behavioral context is sufficient for an agent to decide when to use this tool.

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