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

Beyond readOnlyHint/destructiveHint flags, the description discloses the timeout default/cap, the at-most-once contract, the instruction not to reuse a previous viewer_url while still running, and how to surface concurrency_notice. It also defines follow-up behavior (show job_id and new run_id, only offer email if not already asked), which an agent could not infer from annotations.

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?

Every sentence carries operational guidance; the main purpose and timeout are front-loaded before behavioral rules. There is no filler or repetition of schema/annotations.

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 description covers sequencing, recurrence limits, timeout behavior, viewer_url handling, concurrency_notice, and email-notification policy, so an agent can invoke the tool correctly. It slightly under-specifies the interval_sec parameter, but output schema and annotations cover the return/read-only side, making this a near-complete definition.

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 prose adds real meaning for run_id ('that run's run_id' from create/update) and timeout_sec (default 45, max 90, do not raise to loop). However, job_id's role is only implied and interval_sec is never described, and the schema itself covers only timeout_sec (25%), so the compensation is partial.

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 opening sentence defines a specific action ('Poll a run'), the target resource, and the exact terminal outcomes (completed, failed, cancelled, or timeout). It also names the preceding tools (create_design/update_design), which separates this polling tool from status-reading siblings like check_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?

It explicitly says to call at most once after create_design or update_design and to pass that run's run_id. It gives a when-not rule: if still_running is true, do not call again unless the user explicitly asks, and it points to notify_run_email as the conditional alternative.

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