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

Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds meaningful behavioral context: totals come from daily agg-regates while failure details come from raw deliveries within retention, and it discloses what kinds of failures are returned. This is useful beyond the annotations and contains no contradicction.

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 sentences, front-loaded with the main purpouse, then the delivered output, then the data-source caveat. Every sentence earns its place and there is no filler or redundant restating of the tool name.

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 explains what is returned: delivered, failed, success rate, response time, held-back items, and recent failures with errors. It also clarifies the freshness/aggregation model. It could be slightly richer about how failures_limit/date cutoffs shape the failure sample, but the schema covers most of that.

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 carries most parameter meaning. The description does not add parameter-level details, though it does frame the notion of 'calendar days' and 'per destination'. With high schema coverage, baseline 3 is appriate.

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 verb and resource: it reports delivery health per destination over a date range, with concrete metrics (delivered, failed, success rate, response time, held-back items) and recent failed deliveries with errors. This clearly differentiates it from sibling tools like get_usage or event_stats, even without naming them.

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?

The description provides a clear usage context: for delivery health/status per destination over calendar days. It does not explicitly say when not to use it or name alternative tools, but the purpose is specific enough that an agent can identify when this tool fits. A small exclusion or pointer to siblings would make it fully explicit.

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