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

Annotations already establish readOnlyHint and a closed-world scope, so the bar is lower; the description still adds real behavioral context beyond them – deterministic oldest-first ordering, conditional visibility based on key permission level, and the failure mode for a page-scoped key. It does not discuss pagination or result size, which keeps it at 4.

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 clauses, none wasted: the resource and ordering come first, contents second, access caveats last. Every sentence carries distinct information with no restatement of the name or schema.

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 and no parameters, the description usefully enumerates the returned fields and their ordering, which is the main thing an agent needs. It omits any statement about pagination or maximum result count, a minor gap for a list endpoint.

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 of 4 applies; there is no argument syntax to clarify and the description correctly introduces none. The prose defining 'where each points' describes output, not inputs.

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 specific resource (the account's alert destinations) and elaborates the exact contents of each entry: email addresses, chat channels, pagers, webhooks, the pages that send to them, and confirmation status. Combined with the ordering guarantee ('oldest first'), an agent can distinguish this from get_alert_settings or list_subscribers without opening a schema.

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?

It gives an explicit exclusion ('Not for a key held to one page') and a scope-dependent condition ('A key that writes also sees where each points'), which tells the agent when this call is and isn't appropriate. It stops short of naming a sibling tool to use instead, so it is slightly under 5.

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