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

The description adds synchronous execution, forbidden task support, and detailed output-handling instructions (use assistantSummary, don't display raw JSON, suggest next action). It aligns with annotations (readOnlyHint=true) and provides context beyond the structured fields.

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 first sentence is a clear purpose statement, but the description includes redundant information (e.g., 'Classification: read-only' duplicates readOnlyHint) and a long block of output-presentation instructions that are somewhat tangential. Still, it is structured and front-loaded.

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 polling tool, the description covers purpose, source of tasks, and post-poll behavior. With an output schema present, it doesn't need to describe return structure. It lacks explicit error/retry guidance, but that is partially covered by sibling tools.

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 has 0% description coverage; the description does not explain the three parameters (seatId, taskId, seatName). It only implies taskId via 'returned by build_ad...' but gives no semantics for seatId/seatName, leaving a significant gap for a 3-parameter tool.

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 opens with a specific verb ('Poll') and resource ('durable LeanrIQ task'), names the originating capabilities (build_ad, revise_creative, trafficking), and signals continuation with the completed output. This clearly distinguishes it from siblings like list_tasks, cancel_task, and retry_task.

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 tasks are returned by queued capabilities and that the agent should continue with completed output. It does not explicitly mention alternatives like list_tasks for enumeration or retry_task for failures, but the context of polling a specific task is clear, with no misleading exclusions.

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