List alert deliveries

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

Annotations already declare read-only, idempotent, non-destructive behavior, and the description adds genuinely new context beyond them: the meaning of each status value (pending/delivered/dead/suppressed), the 30-day retention window, newest-page-only pagination, and an explanation of `untrusted_fields` as data LastPing did not write. This is exactly the behavioral detail the annotations cannot carry.

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?

Front-loads the scope requirement, then the resource, then status semantics, then coverage limits. Dense and largely waste-free, though the parenthetical status glosses and the untrusted_fields sentence make it longer than strictly necessary.

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, the description still conveys the row shape (incident event + destination), the possible outcome values, and the retention/pagination envelope, and it flags the untrusted_fields caveat. Nothing an agent needs to call and interpret this correctly is missing.

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 100%, so the baseline is 3, but the prose enriches the semantics of the `status` filter by defining what dead ('per-channel attempt ceiling reached') and suppressed ('destination's rate cap dropped it') actually mean, and explains the row grain the limit/status/monitor filters operate over.

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?

Specific verb+resource ('Lists recent alert deliveries across the project's monitors') with the row grain made explicit — one (incident event, destination) outcome. This is clearly distinguishable from siblings like list_incidents, list_monitors, or list_destinations.

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?

States an access prerequisite ('Requires the read scope or higher') and scopes usage in time and pagination ('Covers 30 days and returns only the newest page'), pointing to the dashboard's delivery log for the archive. It doesn't explicitly contrast with sibling list tools (e.g. list_incidents), so it stops short of full when/when-not routing.

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