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 blocking long-poll behavior, a hard cap of 600 seconds (beyond the schema's 120 default) and how to interpret the returned status. It omits what happens if the run is cancelled, missing, or if the wait errors out.

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?

A single tight sentence with the blocking behavior front-loaded and the timeout/status caveat parenthetical. Nothing is wasted.

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 wait tool with no annotations and no output schema, the description supplies the essential behavior plus return-value interpretation (check `status`). Remaining gaps are edge cases such as run-not-found or cancelled runs and which ID takes precedence.

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%, so the description must explain all three parameters. It only enriches timeout_sec (blocking purpose, max 600, default behavior implied); pipeline_id and run_id are left entirely undocumented beyond self-evident names, and the relationship between the two is unexplained.

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 states a precise behavior: block until the run finishes or the timeout elapses, then return the latest run state. This clearly distinguishes it from non-blocking siblings like pipeline_run_get in practice, though it never names that sibling or restate that it operates on an existing pipeline run.

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 blocking semantics imply it should be used instead of polling pipeline_run_get, and the 'status still running means timed out' note gives the caller a completion check. However, there is no explicit guidance on when to prefer it over polling, no prerequisites, and no mention of what to do on timeout.

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