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

Annotations already carry the safety profile (readOnly, idempotent, non-destructive), so the bar is low; the description nonetheless adds a genuinely useful interpretive caveat: totals derive from daily aggregates while failures come from raw deliveries within retention, which tells the agent why failure data may be truncated or inconsistent with totals.

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?

Two dense sentences, zero filler, with the core subject (per-destination delivery health) and the data-sourcing caveat front-loaded. Every clause carries information an agent can act on.

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 must convey the return shape, and it does — delivered, failed, success rate, response time, held-back counts, and recent failures with errors. The retention caveat covers the main interpretive risk; only minor gaps (pagination, default-org behavior) remain.

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 88%, so the schema already documents from/to/days, destination_id, org, and the failures_* bounds. The description only alludes to the calendar-day range and adds no syntax or format detail beyond the schema, so the baseline 3 is right.

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 resource (delivery health per destination) with a defined scope (range of calendar days) and enumerates the metrics returned. An agent can immediately distinguish this from event_stats or get_usage without opening the 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?

Usage is implied by the content — you call this to inspect delivery reliability and recent failures — but there is no explicit when-to-use, when-not-to-use, or named alternative among the siblings. Adequate but leaves routing to inference.

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