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

Annotations already declare readOnly/openWorld=false, and the description still adds real value: it discloses that a terminal response carries the bounded result and source_anchor for direct consumption, and warns against rerunning the original query. It omits any non-terminal/pending semantics or polling cadence, keeping it short of a 5.

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 tight sentences, front-loaded with the core action and followed by the consumption/warning guidance. No filler or restated annotation content.

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?

With no output schema, the description usefully hints at the terminal payload (bounded result, source_anchor), but it never explains where the opaque task_ref originates, how to interpret non-terminal states, or what the remaining two parameters do—gaps that matter for a polling tool.

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 description coverage is 0% across three parameters, so the description carries the full burden. It only characterizes task_ref as 'opaque'; response_mode (enum 'compact') and connection_context (mctx_v1 pattern) get no explanation, leaving two parameters undocumented anywhere.

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?

States a specific verb and resource ('Poll one opaque task reference'), which is concrete and actionable. However, it does not distinguish itself from close siblings such as google_ads_task_get or google_ads_tasks_list, leaving the agent to infer which poller applies.

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 clause 'never rerun the original query page 1' gives an explicit when-not, steering the agent toward polling instead of re-issuing the original request. It stops short of saying when to poll, how often, or how it relates to the task_get/tasks_list siblings, so usage is only partially covered.

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