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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds substantial context beyond them: pagination defaults and caps (100 default, max 500), the materialization/CSV precondition for recipients existing, the admin-only restriction, the `whatsapp_campaigns` feature requirement, and the ordering guarantee of sync mode ('oldest change first').

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 core purpose, then ordered from preconditions to paging to sync mode to permissions. Every sentence carries operational information; nothing is padding.

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 does much of the return-value work by naming `meta.next_cursor` and describing per-recipient delivery state and change ordering. It stops short of enumerating what a recipient record contains, which is the remaining gap for a read tool whose schema exposes no 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 100%, so the baseline is 3, but the description adds genuine meaning: `cursor` is explained as part of a loop driven by the previous response's `meta.next_cursor` (beyond the schema's terse one-liner), and `replied`/`conversation_display_id` are given intent. It still omits the multi-value filters (`status__`, `stage__`) and field selection behavior.

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 ('List campaign recipients') and immediately scopes what is returned: 'the campaign's recipients in the order they were added, with their delivery state.' The recipient-level granularity distinguishes it from sibling tools like list_whatsapp_campaigns and get_whatsapp_campaign, which operate on campaigns themselves.

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 strong conditional guidance: recipients only exist 'once the campaign has been materialized or a CSV has been imported,' and it explains the incremental-sync pattern (pass `updated_since`, then loop `meta.next_cursor` as `cursor` until `null`). It never names an alternative tool to use instead, so it falls short of the explicit when-not/alternatives bar for a 5.

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