Delivery state per recipient

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds only the endpoint path, which confirms a read on a report subresource; it says nothing about pagination, result limits, retention window for delivery records, or what fields a 'delivery state' contains. No contradiction, but little incremental disclosure.

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?

One short sentence with zero filler, and the endpoint is a useful compact scoping cue. However, being a noun-phrase fragment, it is under-specified rather than genuinely concise in the informative sense.

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?

For a listing tool with an ambiguous single parameter and no output schema, the description should at minimum say what a delivery record looks like (recipient, channel, status, timestamps) and whether results are paginated. None of that is present, so an agent must call blind to discover the response shape.

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 0%, so the description carries the burden for the single 'id' parameter. It partially compensates by embedding {id} in the /v1/reports/{id}/deliveries path, making clear the id is a report identifier rather than a user, workspace, or delivery id. It does not state the id format (numeric vs. UUID) or how to obtain one.

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 description is essentially the title restated ('Delivery state per recipient') plus an HTTP endpoint. The endpoint path does add that this is a read scoped to a specific report ({id}/deliveries), which makes the resource identifiable, but there is no verb and no differentiation from siblings such as reports_get, reports_deliver, notifications_listDeliveries, or conversions_listDeliveries.

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?

No when-to-use guidance at all. With at least three sibling tools that also surface 'deliveries', the agent is given no rule for choosing this one (e.g. 'use after reports_deliver to check per-recipient send status').

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