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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile needs no restating. The description adds genuinely non-obvious context: results are key-scoped, with sandbox keys seeing only sandbox batches and agent keys only their own agent's batches. It stops short of describing pagination traversal or result volume.

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 compact sentences with no filler; the ordering and scope information comes first, and the key-type nuance follows. Every clause carries information an agent would otherwise have to guess.

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 a full output schema and rich annotations, the description only needs to cover access scoping — which it does — and ordering. The one remaining gap is pagination semantics (offset-based traversal, no total-count hint), which is minor given the schema documents limit/offset.

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% — limit, offset, and status are each documented, and status has an enum. The description adds nothing param-specific beyond the 'newest first' ordering note, so the baseline 3 applies when the schema carries the parameter burden.

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 fragment "The caller's batches, newest first" combined with the name clearly identifies a collection-listing operation over batch mail, including scope (caller's own) and ordering. It does not explicitly distinguish itself from siblings like get_batch_mail (single fetch) or list_outbound_mail, but the resource is unambiguous.

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 sentence about sandbox keys vs agent keys tells an agent what it will see, which implicitly frames when the tool is appropriate. However, there is no explicit 'use this instead of X' guidance against get_batch_mail or list_outbound_mail, and no stated preconditions for calling it.

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