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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered; the description usefully adds the rolling 30-day resolved window and the alert taxonomy. It does not state account/credential scope (all campaigns vs. one), result ordering, or volume limits, which are the remaining behavioral unknowns for an alert feed.

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 sentence that front-loads the actionable half ('what needs the human now') and relegates the secondary half ('what cleared') to a trailing clause. The parenthetical carries real content rather than filler; 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?

With zero parameters and an output schema present, the description needn't document return shapes, and it covers the substantive scope (categories plus the 30-day cleared window). The only gap is scope ambiguity — whether alerts span all campaigns/accounts under the current credential — which matters for a triage 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?

The tool takes zero parameters, so the baseline is 4 and there is nothing for the description to disambiguate. The description correctly implies a fixed scope with no caller-supplied filters rather than pretending parameters exist.

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 names a concrete resource (alerts) and enumerates the actual contents — rejected ads, spend spikes, account problems, cap pauses — plus cleared items, so an agent knows exactly what it retrieves. It stops short of differentiating from adjacent siblings like list_ad_suggestions, get_ad_caps, or ad_performance, which overlap with 'rejected ads' and 'cap pauses'.

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?

'What needs the human now' implies a triage use case, and the 30-day window implies a retrospective check, but there is no explicit when-to-use or when-not-to-use statement. No alternative is named, so an agent facing 'cap pauses' cannot tell whether this or get_ad_caps is the right call.

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