alerts

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

With no annotations provided, the description carries the full burden. It explains dedup logic (keeps highest severity per entity), severity thresholds (critical > warning), and warns against speculation. However, it does not disclose authentication needs, rate limits, or side effects.

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 description is concise with two short paragraphs. The core purpose is front-loaded in the first sentence, and the crucial usage note is highlighted separately. No unnecessary repetition.

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?

Given the complexity (3 parameters, no output schema), the description adequately covers purpose and behavior but lacks return value structure. It does not specify what the output looks like beyond 'emits per-entity alerts', which may leave gaps for an AI 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 add meaning. It explains the 'days' parameter via 'last N days vs prior N days' and mentions severity threshold. However, 'site_url' is only indirectly explained via 'per-entity (query+page)', and no details on input format or constraints are given.

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 tool detects regressions by comparing last N days to prior N days, and lists specific alert types (position_drop, ctr_collapse, click_drop, disappeared) and severity levels. This distinguishes it from siblings like traffic_drops.

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 description includes an important usage note about not speculating beyond returned data, but it does not provide explicit guidance on when to use this tool versus alternatives like traffic_drops or content_decay. The context of per-entity alerts is implied but not contrasted.

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