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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description contributes one genuinely useful behavioral fact beyond that: the output is CSV. It says nothing about how the CSV is delivered (inline payload vs. download URL), whether large exports are asynchronous or truncated, or any range limits on the date filters.

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?

It is a single short sentence with no waste, but it is a sentence fragment and not front-loaded with an action verb. Brevity here reflects under-specification rather than efficiency.

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 five parameters, no output schema, and a read-only annotation set, the description should at minimum explain how the CSV comes back and how date filtering scope works. Stating only the output format leaves the agent without the return mechanism it needs given the absence of an output schema.

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 description merely re-lists the enum values of the required 'report' parameter, adding no meaning beyond the schema. The 'sort' parameter has no description in either place, and the relationship between from_date and to_date (and how timezones interact with 'search') is left entirely to the schema's 60% coverage.

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 sentence names the resource (CSV of one of five report types) but is a noun phrase with no verb, so the export/download action is only inferable from the tool name. It also fails to distinguish this from the five closely-related list_* siblings (list_transactions, list_refunds, list_receipts, list_return_labels, list_carrier_adjustments) and export_shipments, which is the most important differentiation an agent needs here.

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 statement of when to choose export_report over the sibling list_* tools or export_shipments, and no mention of prerequisites or limits. The agent must infer the CSV-vs-paginated-list distinction entirely on its own.

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