List conversion deliveries, newest first

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered; the description adds the useful behavioral fact that results come newest-first. It omits other traits that matter for this endpoint, such as whether results are capped at the 500 limit with no paging, and what a delivery record contains.

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 tight sentence with the ordering and endpoint front-loaded and no filler. It is arguably over-terse, but nothing is redundant.

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?

Given a simple read-only tool with three optional params and no output schema, the description is minimally adequate, but it leaves real gaps: status value vocabulary, the meaning of integrationId, and the absence of pagination beyond limit=500. Those matter for calling this correctly on a newest-first listing.

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 only 33% — only status carries a schema description, while limit and integrationId are bare typed fields. The description adds nothing about any parameter: not the valid status strings, not whether integrationId narrows to a single source, and not that limit caps at 500 with no cursor.

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 gives a specific verb and resource ("List conversion deliveries") plus the sort order, and the resource name distinguishes it from the sibling deliveries tools notifications_listDeliveries and reports_listDeliveries. It does not, however, contrast with conversions_listIntegrations or conversions_requeue, so sibling routing still requires inference.

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?

There is no when-to-use guidance at all — nothing says whether this is for auditing failed sends, checking delivery status, or monitoring a specific integration. No exclusions or alternatives (e.g. conversions_requeue, notifications_retryDelivery) are named, so the agent must guess from the name alone.

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