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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely new behavioral facts: a hard 90-day retention window, the fact that skipped deliveries (cooldown, hourly cap, no data) are included rather than filtered out, the delivery_key linkage between an alert and its attached report, and that errors are truncated. These are exactly the traits that change how an agent interprets rows it retrieves.

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?

It is front-loaded with the identifying phrase and every clause carries information (content types, 90-day window, returned fields, skipped rows, key linkage, endpoint mirror). It is dense and slightly run-on as one long sentence, but there is no filler to cut.

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 carries the full burden of describing return values, and it does: the row types, the identifying fields, the grouping key, and the fact that error text is truncated. Combined with the stated 90-day scope and default/max limit, an agent has enough to call this correctly and interpret results.

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?

There is a single parameter with 100% schema description coverage ('Max rows, most recent first, default 500, max 1000'), so the schema already does the work. The description adds no ordering, pagination, or limit guidance beyond what the schema states, which is the baseline-3 case.

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 and enumerates precisely what it contains: alert sends, scheduled reports, reports attached to alerts, and test sends over a fixed 90-day window, along with the fields returned (channel, recipients, trigger_key, window, status, truncated error). That is far beyond a restatement of the name. It loses the top score only because it never contrasts itself with the close sibling list_alert_deliveries, leaving the agent to infer the boundary.

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?

Usage is implied: this is the endpoint behind the Alerts page table, so an agent can infer it is for reviewing what was sent or skipped. But there is no explicit 'use this when…' statement, no exclusion of list_alert_deliveries or list_scheduled_reports, and the final sentence about mirroring GET /api/... is developer provenance rather than selection guidance.

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