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

With no annotations, the description carries full burden. It discloses the polling nature, the terminal response content (bounded result and source_anchor), and a specific behavioral warning (never rerun the original query). It lacks details on non-terminal responses or error behavior, but the key traits are covered.

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?

Two sentences with no filler. The primary action is front-loaded, and the critical warning is included without 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 a simple polling tool, it explains the terminal response and a key constraint, but omits details like what 'bounded result' means, how to interpret non-terminal responses, and the purpose of response_mode. Given the lack of an output schema, these gaps leave some ambiguity 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?

Schema coverage is 0%, so the description must compensate. It clarifies that task_ref is an 'opaque task reference', adding meaning. However, response_mode is not mentioned at all; the schema shows an enum with a default, but the description provides no guidance on when or why to set it. Only half the parameters are addressed.

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 action (poll) and resource (opaque task reference). It distinguishes itself from listing tools by focusing on a single reference, though it doesn't explicitly name sibling alternatives like google_ads_task_get or setup_get_status.

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 provides one exclusion ('never rerun the original query page 1') and implies the tool is for polling after an async operation. However, it doesn't explicitly state when to use this over alternative status tools or mention the prerequisite of having a task_ref from a prior call.

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