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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the bar is lower. The description adds genuinely useful context beyond them: sending runs asynchronously 'at the plan's pace' and delivery states lag each send, so an agent knows results are eventually consistent and partial results are normal.

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 tight sentences with no filler. The primary purpose is front-loaded, and the asynchronous caveat follows as the second thought rather than burying the lead.

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 return-value burden and does it well by listing the recipient states and the reason field for failures, plus the timing caveat. It stops short of stating the counts structure (e.g., message counts per separate batch), a minor gap.

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%, with both 'from' and 'batchId' documented in the schema itself, so baseline 3 applies. The description only loosely reinforces batchId by referencing send_batch and adds no format or syntax detail beyond the schema.

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 and resource ('the state of a batch started with send_batch') and enumerates exactly what the response covers: counts plus every recipient's delivery state. An agent can distinguish this from single-message tools like get_delivery_status 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?

It ties the tool to send_batch by naming it as the producer of the batchId, which implies the flow (send a batch, then poll this). However, it never states when to call it versus alternatives such as get_delivery_status, or how often to poll given the background sending.

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