Alerts

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

Annotations already cover safety (readOnlyHint true, destructiveHint false, openWorldHint true), and the description adds genuinely new context beyond them: the preview API status, the AVADA_API_KEY auth requirement, the fact that only open (not resolved) alerts are returned, and an explicit failure-mode instruction not to fabricate or zero-fill data. It does not describe ordering, pagination, or whether resolved alerts are retrievable, which keeps it off 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?

Three short sentences, front-loaded with the resource and its alert types, then provenance/auth, then failure handling — a sensible priority order. The 'never invent or zero-fill numbers' clause is slightly generic boilerplate but earns its place given the preview API's instability.

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 parameters and no output schema, the description carries the return-value burden and does so by naming the alert kinds the agent will receive, plus auth and failure behavior. Missing only minor operational detail such as whether alerts carry severity, timestamps, or resolution actions.

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 applies; there is nothing for the description to disambiguate. The description correctly avoids inventing filter options that the empty schema does not support, implicitly signalling this is an unfiltered 'give me everything open' call.

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+resource ('Open alerts the app raised') and enumerates the concrete alert categories (tracking stopped, feed failing, campaign not serving, overspend), so an agent can tell this apart from report-style siblings like measurement_get_tracking_health or measurement_get_spend_pacing. It stops short of naming which sibling to use instead when the agent wants resolved or historical alert detail.

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 word 'Open' plus the alert taxonomy implies the use case (surface active problems needing attention), which is adequate context. However, there is no explicit when-to-use/when-not guidance and no routing to the overlapping siblings (measurement_list_feed_issues, measurement_get_setup_status), so selection still requires inference.

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