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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds real operational context beyond that: sending runs in the background at the plan's pace, and delivery states lag the send. That timing nuance is exactly the kind of thing an agent needs to avoid polling confusedly.

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, densely packed, front-loaded with the tool's output. The status list and the timing caveat both earn their place; no filler.

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 burden of describing returns and does so by enumerating the possible states and noting 'failed (with the reason)'. Combined with the lag caveat, an agent has enough to call and interpret this correctly.

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 100%, so both 'from' and 'batchId' are already documented in the schema. The description reinforces that batchId comes from send_batch but adds no format, syntax, or constraint detail beyond the schema — baseline 3.

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 verb+resource ('The state of a batch') and explicitly ties it to the originating sibling, 'started with send_batch'. The enumeration of per-recipient outcomes makes it unmistakable against neighbours like get_delivery_status or list_scheduled.

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 'started with send_batch' and the required batchId, so an agent can infer this is a post-send poll. However, it never says when to prefer this over get_delivery_status, which is a plausible alternative for delivery tracking, nor does it note polling cadence or when the batch is finished.

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