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

With no annotations, the description carries the full burden of behavioral disclosure. It usefully reveals a non-obvious behavior: send success is not delivery confirmation and delivery outcomes appear here. It also names some event states stub. However, it omits other behavioral context such as whether results are paginated, how far back history goes, or whether authorization is required, leaving gaps for a transparent read.

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 with no fluff. The first sentence defines the tool's core purpose and event kinds, and the second adds a critical distinction about queued vs. delivered. Every part earns its place and the most valuable insight is front-loaded.

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?

Although it is a read-style tool, the lack of an output schema and the unexplained 'limit' and 'recipient' parameters leave notable gaps. An agent knows what the tool does but not the shape of the response, the semantics of key parameters, or pagination behavior, so it cannot fully anticipate or validate a call.

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 only 25%, with only 'event' documented in the schema. The description partly compensates by mentioning domain scope ('on this domain') and examples of event values ('accepted, delivered, failed'), but it says nothing about the 'limit' or 'recipient' parametersebb. With most parameters undocumented and no description-level guidance, an agent cannot fully understand the filter options.

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 states 'What happened to messages on this domain' and enumerates event types (accepted, delivered, failed), giving a specific verb and resource. It also distinguishes itself from send_email by explaining that a successful send only means queued, not delivered, making its purpose clear and differentiating it from sibling tools.

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 line 'A send returning success means queued, not delivered; this is where the delivery outcome actually appears' provides a clear context for when to use the tool: after sending, when you need to know the actual delivery result. It implies the tool is for checking outcomes rather than sending, but it does not explicitly contrast with list_messages or list_domains, so exclusion guidance is incomplete.

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