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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds no behavioral context beyond the household scope, such as whether alerts are marked read, how unread is determined, or any ordering/limitations.

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 a single short phrase with no wasted words and the key scope is front-loaded. It is efficient, though it is more of a fragment than a complete sentence.

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 read-only tool with an output schema and strong annotations, the description is minimally viable. However, it relies on the parameter name and sibling context, leaving the notion of 'unread' and the role of household_id unexplained.

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%, so the description must compensate for explaining household_id. It only repeats the word 'household' and does not clarify the parameter's format, optionality, default behavior, or how it affects the returned alerts.

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 states the resource ('unread alerts') and scope ('for the household') clearly, so an agent can infer what this tool returns. However, it is a noun phrase rather than a verb phrase, and it does not explicitly distinguish itself from similar sibling tools like get_signals_recent or get_open_breaches.

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?

There is no guidance about when to use this tool versus alternatives, no prerequisites, and no mention of exclusions. The phrase 'for the household' implies a general read context, but it does not help an agent decide between this and other alert- or household-related tools.

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