dispatch_due_deliveries

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

Annotations already declare destructive=true, idempotentHint=false and openWorldHint=true, but the description adds genuinely non-obvious behavior: it pulls only unsigned payloads from the cloud queue, mints a short-lived JWT locally per payload, and dispatches directly to DoorDash Drive. This external-side-effect and credential-minting detail is exactly the context annotations cannot convey.

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, front-loaded with the action, and each sentence carries distinct information (what fires, how it works end-to-end, when to run it). Slightly verbose in the mechanism chain but nothing is wasted.

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 parameters and no output schema, the description carries the burden well by explaining mechanism, cadence expectation, and that results are reported back. It stops short of 5 by not addressing failure/partial-dispatch behavior or double-firing risk on repeated runs, which matters for a destructive, non-idempotent tool.

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?

The tool takes zero parameters, so the baseline is 4. The description correctly implies the scope is fully determined server-side (the due queue), and there are no parameters whose semantics need explaining.

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 opening sentence gives a specific verb and resource with scope: 'Fire every scheduled delivery that is due right now.' Combined with the explanation of the due-queue source, an agent can distinguish this batch/cadence trigger from single-delivery siblings like dispatch_delivery or dispatch_delivery-style tools without opening any 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?

It states clearly when to invoke it: 'Run it on a cadence (or whenever you want due work flushed)' and explains why the caller must do so ('the cloud backend cannot dispatch anything itself'). It does not name explicit alternatives or state when NOT to use it, so it stops short of a 5.

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