advance_test_batch_mail

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

Goes well beyond the annotations by disclosing concrete side effects: completion 'marks every piece mailed' and 'fires batch.completed to the agent's webhook.' Those effects are invisible from the annotation set, which only says non-readonly, non-destructive, non-idempotent — the webhook emission and bulk state mutation are exactly the context an agent needs before calling.

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?

Three sentences, zero padding, with the hard constraint ('Sandbox keys only') front-loaded before the mechanics and the live-vs-sandbox exclusion last. Every clause carries information.

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?

An output schema exists, so return values need not be described, and the one parameter is fully covered by the schema. The description supplies the state-machine semantics, the side effects, and the sandbox-only restriction — everything an agent needs to invoke it 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 coverage is 100% and the single batch_id is already documented with its provenance (from create_batch_mail or list_batch_mail), so the description has little to add. It does implicitly convey that batch_id identifies a sandbox batch subject to a one-step transition, which is mild added meaning beyond the field type.

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 (simulate/advance) applied to a specific resource (the test batch), and spells out the exact state machine: submitted → in_progress → completed. It also draws the boundary against the live path ('Live batches are advanced by the facility, never by the API'), so an agent can distinguish this sandbox-only tool from the live batch siblings without opening a 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?

'Sandbox keys only' is an explicit precondition, and 'Live batches are advanced by the facility, never by the API' is an explicit exclusion. What's missing is naming the counterpart tool (e.g. advance_test_outbound_mail for single outbound pieces), so an agent must infer from the sibling list which test-advance tool applies.

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