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

Annotations only declare the safety profile (non-read-only, non-destructive, non-idempotent, closed-world). The description adds the behavior that actually matters here: the export runs in the background for up to ~5 minutes, date ranges are limited to the current and 2 previous months, future date_to is silently clamped (surfaced as date_to_clamped_to) while a future date_from is an error, and the final output is a download link. This is substantial disclosure beyond the structured fields.

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?

Front-loaded with the purpose, then ordered by enum semantics, date rules, and polling workflow, with no filler sentences. It is a dense single block without visual breaks, which slightly hurts scanability for a description this long, but every sentence carries load-bearing information.

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 so: it promises an export_id, warns about the date_to_clamped_to field, and explains the terminal download link. Combined with the polling instruction and per-type date rules, an agent has everything needed to call this correctly and handle the response.

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 100%, so the baseline is 3, but the description genuinely adds meaning the schema lacks: the semantics of every export_type enum value (including the deprecated legacy view and its row-granularity distinction), the current-plus-2-months window that appears nowhere in the schema, and the error/clamp asymmetry between date_from and date_to. Some date-requirement text duplicates the schema, which keeps this from a 5.

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?

Opens with a specific verb+resource+format+scope: "Start an asynchronous CSV export of the authenticated customer's data." An agent can immediately separate this from siblings like get_export (poll status) and list_exports (enumerate existing exports), both of which are named or implied.

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?

Gives explicit when-to-use guidance per export_type, states which types require/accept/forbid date ranges, deprecates legacy_inbound_sms in favor of inbound_sms, and names the follow-up tool and workflow: "poll get_export with the returned export_id until it is completed." Nothing about selection is left to inference.

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